initial commit
This commit is contained in:
40
.gitignore
vendored
Normal file
40
.gitignore
vendored
Normal file
@@ -0,0 +1,40 @@
|
||||
# Virtual Environment
|
||||
venv/
|
||||
env/
|
||||
ENV/
|
||||
.venv/
|
||||
|
||||
# Python
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
*.so
|
||||
.Python
|
||||
|
||||
# ArXiv Downloads
|
||||
arxiv_archive/
|
||||
*.pdf
|
||||
|
||||
# Generated Files
|
||||
seen_papers.json
|
||||
latest.html
|
||||
index.html
|
||||
|
||||
# Syncthing
|
||||
.stfolder/
|
||||
.stignore
|
||||
|
||||
# IDE / Editor
|
||||
.vscode/
|
||||
.idea/
|
||||
*.swp
|
||||
*.swo
|
||||
*~
|
||||
|
||||
# OS
|
||||
.DS_Store
|
||||
Thumbs.db
|
||||
desktop.ini
|
||||
|
||||
# Logs
|
||||
*.log
|
||||
21
LICENSE
Normal file
21
LICENSE
Normal file
@@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2025
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
203
README.md
Normal file
203
README.md
Normal file
@@ -0,0 +1,203 @@
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# 📚 Research Digest
|
||||
|
||||
**Automated daily research paper digest from arXiv with smart filtering, mobile-friendly interface, and AI-powered summaries.**
|
||||
|
||||
Fetch, filter, and browse the latest research papers tailored to your interests. Desktop grid view for deep reading, mobile feed for quick scrolling.
|
||||
|
||||
---
|
||||
|
||||
## ✨ Features
|
||||
|
||||
- **🎯 Smart Filtering** - Keyword-based relevance scoring across custom research interests
|
||||
- **📱 Mobile Feed** - Swipeable, full-screen card interface optimized for phones
|
||||
- **🖥️ Desktop Grid** - Multi-column layout with rich metadata and difficulty badges
|
||||
- **🧠 AI Summaries** - Auto-generated layman explanations using transformers
|
||||
- **🔄 Deduplication** - Never see the same paper twice with built-in tracking
|
||||
- **⚙️ Configurable** - JSON-based settings for interests, filters, and preferences
|
||||
- **📦 Archive** - Auto-saves daily digests with browsable index
|
||||
|
||||
---
|
||||
|
||||
## 🖼️ Screenshots
|
||||
|
||||
### Desktop View
|
||||
|
||||
|
||||
### Mobile Feed
|
||||
|
||||
|
||||
---
|
||||
|
||||
## 🚀 Quick Start
|
||||
|
||||
### Windows
|
||||
|
||||
1. **Clone & Run**
|
||||
```bash
|
||||
git clone https://github.com/yourusername/research-digest.git
|
||||
cd research-digest
|
||||
run_digest.bat
|
||||
```
|
||||
|
||||
2. **First run automatically:**
|
||||
- Creates virtual environment
|
||||
- Installs dependencies
|
||||
- Fetches papers
|
||||
- Generates HTML digests
|
||||
|
||||
3. **Open in browser:**
|
||||
- `latest.html` - Most recent digest
|
||||
- `index.html` - Browse all archives
|
||||
- `tiktok_feed.html` - Mobile-optimized feed
|
||||
|
||||
### Linux/macOS
|
||||
|
||||
```bash
|
||||
git clone https://github.com/yourusername/research-digest.git
|
||||
cd research-digest
|
||||
python -m venv venv
|
||||
source venv/bin/activate # On Windows: venv\Scripts\activate
|
||||
pip install -r requirements.txt
|
||||
python main.py
|
||||
python generate_index.py
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## ⚙️ Configuration
|
||||
|
||||
Edit `config.json` to customize:
|
||||
|
||||
```json
|
||||
{
|
||||
"interests": {
|
||||
"Your Research Area": {
|
||||
"query": "cat:cs.LG OR cat:cs.AI",
|
||||
"keywords": ["keyword1", "keyword2", "keyword3"]
|
||||
}
|
||||
},
|
||||
"settings": {
|
||||
"papers_per_interest": 10,
|
||||
"recent_days": 7,
|
||||
"summary_max_length": 160
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Available Settings
|
||||
|
||||
| Setting | Default | Description |
|
||||
|---------|---------|-------------|
|
||||
| `papers_per_interest` | 10 | Papers to fetch per category |
|
||||
| `recent_days` | 7 | Look back window (0 = all time) |
|
||||
| `fallback_days` | 90 | Extended search if few results |
|
||||
| `summary_max_length` | 160 | Max characters for summaries |
|
||||
| `fetch_multiplier` | 5 | Over-fetch for better filtering |
|
||||
|
||||
---
|
||||
|
||||
## 📖 arXiv Query Syntax
|
||||
|
||||
Use arXiv category codes in queries:
|
||||
|
||||
- `cat:cs.LG` - Machine Learning
|
||||
- `cat:cs.CV` - Computer Vision
|
||||
- `cat:cs.CL` - Computation & Language (NLP)
|
||||
- `cat:cs.AI` - Artificial Intelligence
|
||||
- `cat:cs.CR` - Cryptography & Security
|
||||
- `cat:cs.DC` - Distributed Computing
|
||||
|
||||
Combine with `OR`/`AND`: `cat:cs.LG OR cat:cs.AI`
|
||||
|
||||
[Full category list](https://arxiv.org/category_taxonomy)
|
||||
|
||||
---
|
||||
|
||||
## 🔧 Advanced Usage
|
||||
|
||||
### Automated Daily Digests
|
||||
|
||||
**Windows Task Scheduler:**
|
||||
1. Open Task Scheduler
|
||||
2. Create Basic Task → Daily → 7:00 AM
|
||||
3. Action: Start Program → `C:\path\to\run_digest.bat`
|
||||
|
||||
**Linux/macOS Cron:**
|
||||
```bash
|
||||
0 7 * * * cd /path/to/research-digest && ./venv/bin/python main.py && ./venv/bin/python generate_index.py
|
||||
```
|
||||
|
||||
### Sync to Mobile (Syncthing)
|
||||
|
||||
1. Install [Syncthing](https://syncthing.net/) on PC and phone
|
||||
2. Share project folder
|
||||
3. Access HTML files directly on phone
|
||||
|
||||
### Reset Seen Papers
|
||||
|
||||
```bash
|
||||
python reset_seen_papers.py
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📂 Project Structure
|
||||
|
||||
```
|
||||
research-digest/
|
||||
├── config.json # Configuration (edit this!)
|
||||
├── main.py # Core paper fetcher
|
||||
├── generate_index.py # Archive browser generator
|
||||
├── generate_tiktok_feed.py # Mobile feed generator
|
||||
├── run_digest.bat # Windows launcher
|
||||
├── requirements.txt # Python dependencies
|
||||
├── latest.html # Latest digest (auto-generated)
|
||||
├── index.html # Archive browser (auto-generated)
|
||||
├── tiktok_feed.html # Mobile feed (auto-generated)
|
||||
├── seen_papers.json # Deduplication tracker
|
||||
└── arxiv_archive/ # Daily archives
|
||||
├── arxiv_digest_20251101.html
|
||||
└── ...
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🛠️ Requirements
|
||||
|
||||
- **Python 3.8+**
|
||||
- **Dependencies:** `transformers`, `torch`, `requests`
|
||||
- **Disk Space:** ~2GB for model, ~10MB per digest
|
||||
- **Internet:** Required for arXiv API and first-time model download
|
||||
|
||||
---
|
||||
|
||||
## 📝 License
|
||||
|
||||
MIT License - see [LICENSE](LICENSE) file for details
|
||||
|
||||
---
|
||||
|
||||
## 🤝 Contributing
|
||||
|
||||
Contributions welcome! Ideas:
|
||||
- Additional paper sources (bioRxiv, SSRN, etc.)
|
||||
- Browser extension for direct syncing
|
||||
- Custom ML models for better summaries
|
||||
- Export to Notion/Obsidian/Roam
|
||||
|
||||
---
|
||||
|
||||
## 🙏 Acknowledgments
|
||||
|
||||
- [arXiv](https://arxiv.org/) for the open research repository
|
||||
- [Hugging Face](https://huggingface.co/) for transformer models
|
||||
- Inspired by modern feed UIs and research workflows
|
||||
|
||||
---
|
||||
|
||||
**Built with ❤️ for researchers who want to stay current without drowning in papers**
|
||||
198
SETUP_GUIDE.md
Normal file
198
SETUP_GUIDE.md
Normal file
@@ -0,0 +1,198 @@
|
||||
# 📱 Syncthing + Daily arXiv Digest Setup Guide
|
||||
|
||||
## 🎯 What This Does
|
||||
- Automatically runs your arXiv digest **every morning at 7 AM**
|
||||
- Archives each day's report in `arxiv_archive/`
|
||||
- Creates `latest.html` for quick access
|
||||
- Generates `index.html` to browse all past reports
|
||||
- Syncs everything to your phone via Syncthing
|
||||
|
||||
---
|
||||
|
||||
## ⚙️ Step 1: Set Up Windows Task Scheduler
|
||||
|
||||
### Option A: Quick Setup (Copy-Paste This)
|
||||
1. Press `Win + R`, type `taskschd.msc`, press Enter
|
||||
2. Click **"Create Basic Task"** in the right panel
|
||||
3. Fill in:
|
||||
- **Name:** `arXiv Daily Digest`
|
||||
- **Description:** `Fetches daily research papers and syncs to phone`
|
||||
4. **Trigger:** Select "Daily"
|
||||
- Start date: Today
|
||||
- Start time: **7:00 AM**
|
||||
- Recur every: **1 days**
|
||||
5. **Action:** Select "Start a program"
|
||||
- **Program/script:** `C:\Users\Admin\python\1aResearch\run_digest.bat`
|
||||
- **Start in:** `C:\Users\Admin\python\1aResearch`
|
||||
6. Check **"Open the Properties dialog"** at the end
|
||||
7. In Properties:
|
||||
- Go to **Conditions** tab
|
||||
- ✅ Check "Start only if the following network connection is available" → Select "Any connection"
|
||||
- ❌ Uncheck "Start the task only if the computer is on AC power"
|
||||
8. Click **OK**
|
||||
|
||||
### Option B: Advanced Settings
|
||||
If you want to run it at startup instead:
|
||||
- Change Trigger to **"At log on"**
|
||||
- Add a 2-minute delay: In Properties → Triggers → Edit → Delay task for: **2 minutes**
|
||||
|
||||
---
|
||||
|
||||
## 📂 Step 2: Set Up Syncthing
|
||||
|
||||
### On Your PC:
|
||||
1. Open Syncthing web UI (usually `http://localhost:8384`)
|
||||
2. Click **"Add Folder"**
|
||||
- **Folder Path:** `C:\Users\Admin\python\1aResearch`
|
||||
- **Folder Label:** `arXiv Research`
|
||||
- **Folder ID:** `arxiv-research` (auto-generated)
|
||||
3. Go to **"Sharing"** tab
|
||||
4. Click **"Add Device"** and enter your phone's Device ID
|
||||
|
||||
### On Your Phone:
|
||||
1. Install **Syncthing** from Play Store / App Store
|
||||
2. Open app → **Add Device** → Scan QR code from PC
|
||||
3. Accept the folder share request (`arXiv Research`)
|
||||
4. Set sync folder location (e.g., `/storage/emulated/0/arXiv/`)
|
||||
|
||||
### What Gets Synced:
|
||||
```
|
||||
1aResearch/
|
||||
├── latest.html ← Most recent digest (quick access)
|
||||
├── index.html ← Browse all reports
|
||||
└── arxiv_archive/
|
||||
├── arxiv_digest_20251101.html
|
||||
├── arxiv_digest_20251102.html
|
||||
└── ... (daily backups)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📱 Step 3: View on Your Phone
|
||||
|
||||
### Method 1: Direct File Access
|
||||
1. Open your phone's file manager
|
||||
2. Navigate to the Syncthing folder (e.g., `arXiv/`)
|
||||
3. Open `latest.html` with any browser
|
||||
4. Open `index.html` to browse past reports
|
||||
|
||||
### Method 2: Use a Local HTML Viewer App
|
||||
Install **"HTML Viewer"** or **"WebView Tester"** from the app store:
|
||||
- Point it to your Syncthing folder
|
||||
- Bookmark `latest.html` for instant access
|
||||
|
||||
### Method 3: Create a Home Screen Shortcut (Android)
|
||||
1. Open `latest.html` in Chrome
|
||||
2. Menu → **"Add to Home screen"**
|
||||
3. Name it "arXiv Digest"
|
||||
4. Now you have one-tap access!
|
||||
|
||||
---
|
||||
|
||||
## 🧪 Testing Your Setup
|
||||
|
||||
### Test the Batch Script:
|
||||
```batch
|
||||
# Double-click run_digest.bat or run in Command Prompt:
|
||||
cd C:\Users\Admin\python\1aResearch
|
||||
run_digest.bat
|
||||
```
|
||||
|
||||
Expected output:
|
||||
```
|
||||
Running arXiv digest...
|
||||
🔍 Fetching papers for: Efficient ML / Edge AI
|
||||
→ Found 5 papers
|
||||
...
|
||||
✨ HTML digest saved to arxiv_archive\arxiv_digest_20251101.html
|
||||
📄 Latest digest saved to latest.html
|
||||
|
||||
Generating index page...
|
||||
📑 Index page generated with 1 reports
|
||||
Done! All files updated.
|
||||
```
|
||||
|
||||
### Test Syncthing Sync:
|
||||
1. Create/edit any file in `C:\Users\Admin\python\1aResearch`
|
||||
2. Check your phone's Syncthing folder
|
||||
3. File should appear within seconds
|
||||
|
||||
### Test Task Scheduler:
|
||||
1. Open Task Scheduler
|
||||
2. Find "arXiv Daily Digest"
|
||||
3. Right-click → **"Run"**
|
||||
4. Watch it execute
|
||||
|
||||
---
|
||||
|
||||
## 🎨 Customization Ideas
|
||||
|
||||
### Change Run Time:
|
||||
Edit the Task Scheduler trigger to your preferred time (e.g., 6 AM, 9 PM)
|
||||
|
||||
### Change Number of Papers:
|
||||
Edit `main.py` line 21:
|
||||
```python
|
||||
PAPERS_PER_INTEREST = 10 # Fetch 10 instead of 5
|
||||
```
|
||||
|
||||
### Add More Interest Areas:
|
||||
Edit `main.py` lines 13-19 and add more queries:
|
||||
```python
|
||||
INTERESTS = {
|
||||
"Your Topic": 'abs:"your keywords" OR ti:"your topic"',
|
||||
# ... existing topics
|
||||
}
|
||||
```
|
||||
|
||||
### Sync Only HTML Files (Save Space):
|
||||
In Syncthing → Folder → **Ignore Patterns**, add:
|
||||
```
|
||||
!/arxiv_archive/*.html
|
||||
!/latest.html
|
||||
!/index.html
|
||||
*
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🔧 Troubleshooting
|
||||
|
||||
### Task Scheduler doesn't run:
|
||||
- Check Windows Event Viewer: `Win + X` → Event Viewer → Task Scheduler logs
|
||||
- Ensure "Run whether user is logged on or not" is selected
|
||||
- Make sure network connection is available
|
||||
|
||||
### Syncthing not syncing:
|
||||
- Check both devices are connected to the same network (or internet)
|
||||
- Verify Device IDs match
|
||||
- Check folder status in Syncthing UI (should say "Up to Date")
|
||||
|
||||
### Python script fails:
|
||||
- Test manually: `cd C:\Users\Admin\python\1aResearch && venv\Scripts\activate && python main.py`
|
||||
- Check arXiv API rate limits (3-second delays are built in)
|
||||
- Ensure internet connection is active
|
||||
|
||||
### Old reports taking up space:
|
||||
Create a cleanup script to delete reports older than 30 days:
|
||||
```python
|
||||
# cleanup_old.py
|
||||
import os, glob, time
|
||||
for f in glob.glob("arxiv_archive/*.html"):
|
||||
if os.path.getmtime(f) < time.time() - 30*86400:
|
||||
os.remove(f)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🎉 You're All Set!
|
||||
|
||||
Every morning at 7 AM:
|
||||
1. ✅ Script fetches latest papers
|
||||
2. ✅ Generates beautiful HTML report
|
||||
3. ✅ Archives it with date
|
||||
4. ✅ Updates index page
|
||||
5. ✅ Syncs to your phone
|
||||
6. ✅ Read cutting-edge research over coffee!
|
||||
|
||||
**Enjoy your automated research digest! 🚀**
|
||||
985
arxiv_digest_20251101.html
Normal file
985
arxiv_digest_20251101.html
Normal file
@@ -0,0 +1,985 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
|
||||
<title>arXiv Digest • 2025-11-01</title>
|
||||
<style>
|
||||
* { box-sizing: border-box; }
|
||||
|
||||
:root {
|
||||
--bg: #0f0f0f;
|
||||
--text: #e8e8e8;
|
||||
--muted: #999;
|
||||
--border: #2a2a2a;
|
||||
--card-bg: #1a1a1a;
|
||||
--link: #6ba3ff;
|
||||
--accent: #ff6b6b;
|
||||
--green: #51cf66;
|
||||
--yellow: #ffd43b;
|
||||
--red: #ff6b6b;
|
||||
--layman-bg: #1f2937;
|
||||
--layman-border: #60a5fa;
|
||||
}
|
||||
|
||||
body {
|
||||
font-family: 'Inter', -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
|
||||
line-height: 1.5;
|
||||
color: var(--text);
|
||||
background: var(--bg);
|
||||
margin: 0;
|
||||
padding: 1rem;
|
||||
}
|
||||
|
||||
.container {
|
||||
max-width: 1600px;
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
header {
|
||||
text-align: center;
|
||||
padding: 2rem 1rem 3rem;
|
||||
border-bottom: 2px solid var(--border);
|
||||
margin-bottom: 2rem;
|
||||
}
|
||||
|
||||
h1 {
|
||||
font-weight: 900;
|
||||
font-size: 2.5rem;
|
||||
margin: 0;
|
||||
background: linear-gradient(135deg, var(--accent), #ffa94d);
|
||||
-webkit-background-clip: text;
|
||||
-webkit-text-fill-color: transparent;
|
||||
background-clip: text;
|
||||
}
|
||||
|
||||
.meta {
|
||||
color: var(--muted);
|
||||
font-size: 0.95rem;
|
||||
margin-top: 0.5rem;
|
||||
letter-spacing: 0.5px;
|
||||
}
|
||||
|
||||
.interest-section {
|
||||
margin-bottom: 3rem;
|
||||
}
|
||||
|
||||
.interest-header {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 0.8rem;
|
||||
margin-bottom: 1.2rem;
|
||||
padding: 0.8rem 1rem;
|
||||
background: var(--card-bg);
|
||||
border-radius: 12px;
|
||||
border-left: 4px solid var(--accent);
|
||||
}
|
||||
|
||||
.interest-title {
|
||||
font-size: 1.3rem;
|
||||
margin: 0;
|
||||
font-weight: 700;
|
||||
color: var(--text);
|
||||
}
|
||||
|
||||
.papers-grid {
|
||||
display: grid;
|
||||
grid-template-columns: repeat(auto-fill, minmax(380px, 1fr));
|
||||
gap: 1.2rem;
|
||||
}
|
||||
|
||||
.paper {
|
||||
background: var(--card-bg);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 12px;
|
||||
padding: 1.2rem;
|
||||
transition: all 0.2s ease;
|
||||
position: relative;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
height: 100%;
|
||||
}
|
||||
|
||||
.paper:hover {
|
||||
border-color: var(--accent);
|
||||
transform: translateY(-2px);
|
||||
box-shadow: 0 8px 24px rgba(255, 107, 107, 0.15);
|
||||
}
|
||||
|
||||
.paper-header {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: flex-start;
|
||||
gap: 0.8rem;
|
||||
margin-bottom: 0.8rem;
|
||||
}
|
||||
|
||||
.difficulty-badge {
|
||||
padding: 0.3rem 0.7rem;
|
||||
border-radius: 20px;
|
||||
font-size: 0.7rem;
|
||||
font-weight: 700;
|
||||
white-space: nowrap;
|
||||
flex-shrink: 0;
|
||||
}
|
||||
|
||||
.paper h3 {
|
||||
font-size: 1.05rem;
|
||||
margin: 0 0 0.8rem 0;
|
||||
font-weight: 700;
|
||||
line-height: 1.4;
|
||||
color: var(--text);
|
||||
}
|
||||
|
||||
.layman-box {
|
||||
background: var(--layman-bg);
|
||||
border-left: 3px solid var(--layman-border);
|
||||
padding: 0.7rem 0.9rem;
|
||||
margin-bottom: 0.8rem;
|
||||
border-radius: 6px;
|
||||
font-size: 0.88rem;
|
||||
line-height: 1.5;
|
||||
color: #94a3b8;
|
||||
font-style: italic;
|
||||
}
|
||||
|
||||
.summary {
|
||||
color: var(--muted);
|
||||
margin-bottom: 1rem;
|
||||
font-size: 0.88rem;
|
||||
line-height: 1.6;
|
||||
flex-grow: 1;
|
||||
}
|
||||
|
||||
.paper-footer {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
padding-top: 0.8rem;
|
||||
border-top: 1px solid var(--border);
|
||||
margin-top: auto;
|
||||
}
|
||||
|
||||
.category-tag {
|
||||
background: #1e3a5f;
|
||||
color: #60a5fa;
|
||||
padding: 0.25rem 0.65rem;
|
||||
border-radius: 15px;
|
||||
font-size: 0.75rem;
|
||||
font-weight: 600;
|
||||
}
|
||||
|
||||
.date {
|
||||
color: var(--muted);
|
||||
font-size: 0.75rem;
|
||||
}
|
||||
|
||||
.links {
|
||||
display: flex;
|
||||
gap: 1rem;
|
||||
margin-top: 0.8rem;
|
||||
}
|
||||
|
||||
.links a {
|
||||
color: var(--link);
|
||||
text-decoration: none;
|
||||
font-size: 0.85rem;
|
||||
font-weight: 600;
|
||||
transition: color 0.2s;
|
||||
}
|
||||
|
||||
.links a:hover {
|
||||
color: var(--accent);
|
||||
}
|
||||
|
||||
.footer {
|
||||
text-align: center;
|
||||
margin-top: 4rem;
|
||||
padding: 2rem;
|
||||
color: var(--muted);
|
||||
font-size: 0.85rem;
|
||||
border-top: 1px solid var(--border);
|
||||
}
|
||||
|
||||
@media (max-width: 768px) {
|
||||
.papers-grid {
|
||||
grid-template-columns: 1fr;
|
||||
}
|
||||
h1 {
|
||||
font-size: 2rem;
|
||||
}
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div class="container">
|
||||
<header>
|
||||
<h1>arXiv Research Digest</h1>
|
||||
<div class="meta">November 01, 2025 • 45 papers across 5 interests</div>
|
||||
</header>
|
||||
<section class="interest-section">
|
||||
<div class="interest-header">
|
||||
<span>🔬</span>
|
||||
<h2 class="interest-title">Efficient ML / Edge AI</h2>
|
||||
</div>
|
||||
<div class="papers-grid">
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Inference-Cost-Aware Dynamic Tree Construction for Efficient Inference in Large Language Models</h3>
|
||||
<div class="layman-box">💡 This research tackles the problem of language AI.</div>
|
||||
<div class="summary"> Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size . To address this, speculative decoding emerges as a solution, enabling the simultaneous generation and validation of multiple tokens .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CL</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26577v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26577.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual</h3>
|
||||
<div class="layman-box">💡 This research reduces language AI.</div>
|
||||
<div class="summary"> Knowledge distillation (KD) demonstrates promising results in transferring knowledge from larger to smaller VLMs . applying KD in multilingualism is an underexplored area . We study five distillation formulations across CLIP and SigLIP2 .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CL</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26271v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26271.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>STAR: A Privacy-Preserving, Energy-Efficient Edge AI Framework for Human Activity Recognition via Wi-Fi CSI in Mobile and Pervasive Computing Environments</h3>
|
||||
<div class="layman-box">💡 This research presents techniques for privacy-preserving AI.</div>
|
||||
<div class="summary"> Human Activity Recognition (HAR) via Wi-Fi Channel State Information (CSI) presents a privacy-preserving, contactless sensing approach suitable for smart homes, healthcare monitoring, and mobile IoT systems .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26148v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26148.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods</h3>
|
||||
<div class="layman-box">💡 This research running AI locally on devices for computer vision.</div>
|
||||
<div class="summary"> Knowledge distillation (KD) is an effective method for model compression and transferring knowledge between models . However, its effect on model's robustness against spurious correlations that degrade performance on out-of-distribution data remains underexplored . This study investigates the effect of knowledge distillation on the transferability of ``debiasing'' capabilities from teacher models to student models .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26038v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26038.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>An Agentic Framework for Rapid Deployment of Edge AI Solutions in Industry 5.0</h3>
|
||||
<div class="layman-box">💡 This research reduces edge computing.</div>
|
||||
<div class="summary"> We present a novel framework for Industry 5.0 that simplifies the deployment of AI models on edge devices in various industrial settings . The design reduces latency and avoids external data transfer by enabling local inference and real-time processing .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.AI</span>
|
||||
<span class="date">2025-10-29</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.25813v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.25813.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Energy-Efficient Autonomous Driving with Adaptive Perception and Robust Decision</h3>
|
||||
<div class="layman-box">💡 This research explores techniques in machine learning.</div>
|
||||
<div class="summary"> Autonomous driving is an emerging technology that is expected to bring significant social, economic, and environmental benefits . However, these benefits come with rising energy consumption by computation engines limiting the driving range of vehicles, especially electric ones . Perception computing is typically the most power-intensive component, as it relies on deep learning models to extract environmental features . To address these challenges, we propose an energy-efficient autonomous driving framework, called EneAD .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.AI</span>
|
||||
<span class="date">2025-10-29</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.25205v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.25205.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Resource-Efficient and Robust Inference of Deep and Bayesian Neural Networks on Embedded and Analog Computing Platforms</h3>
|
||||
<div class="layman-box">💡 This research makes more efficient edge computing.</div>
|
||||
<div class="summary"> While machine learning has transformed numerous application domains, its growing computational demands increasingly constrain scalability and efficiency . In practice, neural networks must not only operate efficiently but also provide reliable predictions under distributional shifts or unseen data . This work advances resource-efficient and robust inference for both conventional and Bayesian neural networks .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-28</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.24951v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.24951.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>UHKD: A Unified Framework for Heterogeneous Knowledge Distillation via Frequency-Domain Representations</h3>
|
||||
<div class="layman-box">💡 This research reduces computer vision.</div>
|
||||
<div class="summary"> Knowledge distillation (KD) is an effective model compression technique that transfers knowledge from a high-performance teacher to a lightweight student, reducing cost while maintaining accuracy . In visual applications, where large-scale image models are widely used, KD enables efficient deployment .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CV</span>
|
||||
<span class="date">2025-10-28</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.24116v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.24116.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>A Survey on Efficient Vision-Language-Action Models</h3>
|
||||
<div class="layman-box">💡 This research presents techniques for computer vision.</div>
|
||||
<div class="summary"> Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-world interaction . While these models have demonstrated remarkable generalist capabilities, deployment is severely hampered by the substantial computational and data requirements .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CV</span>
|
||||
<span class="date">2025-10-27</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.24795v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.24795.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions</h3>
|
||||
<div class="layman-box">💡 This research running AI locally on devices for language AI.</div>
|
||||
<div class="summary"> Edge intelligent applications like VR/AR and language model based chatbots have become widespread with the rapid expansion of IoT and mobile devices . But constrained edge devices often cannot serve the increasingly large and complex deep learning (DL) models . Research aims to balance accuracy, computation delay, transmission delay, and privacy concerns .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.DC</span>
|
||||
<span class="date">2025-10-27</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.22909v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.22909.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
</div>
|
||||
</section>
|
||||
<section class="interest-section">
|
||||
<div class="interest-header">
|
||||
<span>🔬</span>
|
||||
<h2 class="interest-title">Privacy-Preserving ML</h2>
|
||||
</div>
|
||||
<div class="papers-grid">
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-off</h3>
|
||||
<div class="layman-box">💡 This research distributed machine learning across computer vision.</div>
|
||||
<div class="summary"> Over-the-air (OTA) federated learning (FL) has been well recognized as a scalable paradigm that exploits the waveform superposition of the wireless multiple-access channel . We develop novel OTA-FL SGD updates that allow a structured, time-invariant model bias while facilitating reduced variance updates .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26722v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26722.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟡 Advanced</span>
|
||||
</div>
|
||||
<h3>On Purely Private Covariance Estimation</h3>
|
||||
<div class="layman-box">💡 This research presents techniques for privacy-preserving AI.</div>
|
||||
<div class="summary"> We present a simple perturbation mechanism for the release of $d-dimensional covariance matrices under pure differential privacy . For large datasets with at least $n\geq d^2/\varepsilon elements, our mechanism recovers the provably optimal Frobenius norm error guarantees of \cite{nikolov2023private}.</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26717v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26717.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Tight Differentially Private PCA via Matrix Coherence</h3>
|
||||
<div class="layman-box">💡 This research makes more efficient privacy-preserving AI.</div>
|
||||
<div class="summary"> We revisit the task of computing the span of the top $r$ singular vectors $u_1, \ldots, u_r$ of a matrix under differential privacy . We show that a simple and efficient algorithm -- based on singular value decomposition and standard perturbation mechanisms -- returns a private rank-$r$ approximation whose error depends only on the coherence of the input .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26679v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26679.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>UnifiedFL: A Dynamic Unified Learning Framework for Equitable Federation</h3>
|
||||
<div class="layman-box">💡 This research protecting data privacy in privacy-preserving AI.</div>
|
||||
<div class="summary"> Federated learning (FL) has emerged as a key paradigm for collaborative model training across multiple clients without sharing raw data . We propose UnifiedFL, a dynamic federated learning framework that represents heterogeneous local networks as nodes and edges in a directed model graph optimized by a shared graph neural network .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26350v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26350.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>PEEL: A Poisoning-Exposing Encoding Theoretical Framework for Local Differential Privacy</h3>
|
||||
<div class="layman-box">💡 This research protecting data privacy in privacy-preserving AI.</div>
|
||||
<div class="summary"> Local Differential Privacy (LDP) is a widely adopted privacy-protection model in the Internet of Things . However, existing defenses either incur prohibitive resource overheads or rely on domain-specific prior knowledge . We propose PEEL, a Poisoning-Exposing Encoding theoretical framework for LDP, which departs from resource- or prior-dependent countermeasures . PEEL amplifies stealthy poisoning effects by re-encoding LDP-perturbed data via sparsification, normalization, and low-rank projection .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CR</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26102v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26102.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
</div>
|
||||
</section>
|
||||
<section class="interest-section">
|
||||
<div class="interest-header">
|
||||
<span>🔬</span>
|
||||
<h2 class="interest-title">Creative AI / Emotion</h2>
|
||||
</div>
|
||||
<div class="papers-grid">
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Contribution-Guided Asymmetric Learning for Robust Multimodal Fusion under Imbalance and Noise</h3>
|
||||
<div class="layman-box">💡 This research achieves better emotion AI.</div>
|
||||
<div class="summary"> Contribution-Guided Asymmetric Learning (CAL) aims to enhance the contribution of high-contribution modalities while compressing weak modalities to increase their contribution . CAL has shown outstanding performance in imbalanced fusion tasks and noise robustness tests . CAL is based on a modality contribution metric W^m combining the information quantity I(m) and confidence D(m).</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.MM</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26289v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26289.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Lost in Phonation: Voice Quality Variation as an Evaluation Dimension for Speech Foundation Models</h3>
|
||||
<div class="layman-box">💡 This research presents techniques for speech processing.</div>
|
||||
<div class="summary"> Recent advances in speech foundation models (SFMs) have enabled the direct processing of spoken language from raw audio . This capability allows SFMs to be exposed to rich paralinguistic variations embedded in the input speech signal . One under-explored dimension of this variation is voice quality, encompassing phonation types such as creaky and breathy voice .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">eess.AS</span>
|
||||
<span class="date">2025-10-29</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.25577v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.25577.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Evaluating Emotion Recognition in Spoken Language Models on Emotionally Incongruent Speech</h3>
|
||||
<div class="layman-box">💡 This research achieves better language AI.</div>
|
||||
<div class="summary"> Advances in spoken language processing have driven the development of spoken language models . We evaluate four SLMs on the task of speech emotion recognition using a dataset of emotionally incongruent speech samples . Results indicate that SLMs rely predominantly on textual semantics rather than speech emotion to perform the task .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CL</span>
|
||||
<span class="date">2025-10-29</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.25054v2" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.25054.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>MCIHN: A Hybrid Network Model Based on Multi-path Cross-modal Interaction for Multimodal Emotion Recognition</h3>
|
||||
<div class="layman-box">💡 This research understanding emotions in emotion AI.</div>
|
||||
<div class="summary"> Multimodal emotion recognition is crucial for future human-computer interaction . However accurate emotion recognition still faces significant challenges due to differences between different modalities and the difficulty of characterizing unimodal emotional information . A hybrid network model based on multipath cross-modal interaction (MCIHN) is proposed .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CV</span>
|
||||
<span class="date">2025-10-28</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.24827v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.24827.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier</h3>
|
||||
<div class="layman-box">💡 This research understanding emotions in language AI.</div>
|
||||
<div class="summary"> Emotional Rationale Verifier (ERV) and an Explanation Reward are novel approaches to predicting emotions . Authors propose a novel approach: the ERV and an explanation reward . Their method significantly improves explanation-prediction consistency and explanation emotion accuracy .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.AI</span>
|
||||
<span class="date">2025-10-27</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.23506v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.23506.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Emotion Recognition with Minimal Wearable Sensing: Multi-domain Feature, Hybrid Feature Selection, and Personalized vs. Generalized Ensemble Model Analysis</h3>
|
||||
<div class="layman-box">💡 This research proposes a method for edge computing.</div>
|
||||
<div class="summary"> Negative emotions are linked to the onset of neurodegenerative diseases and dementia . Physiological signals from wearable devices offer a promising noninvasive method for continuous emotion monitoring . The method is designed for deployment in resource-constrained systems, such as Internet of Things .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.HC</span>
|
||||
<span class="date">2025-10-26</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.22498v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.22498.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis</h3>
|
||||
<div class="layman-box">💡 This research explores techniques in emotion AI.</div>
|
||||
<div class="summary"> LUNA (Latent Unified Network Architecture) is a self-supervised foundation model that reconciles disparate electrode geometries while scaling linearly -- not quadratically -- with channel count . LUNA compresses multi-channel EEG into a fixed-size, topology-agnostic latent space via learned queries and cross-attention . It demonstrates highly competitive performance across several benchmarks .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-25</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.22257v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.22257.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing</h3>
|
||||
<div class="layman-box">💡 This research presents techniques for emotion AI.</div>
|
||||
<div class="summary"> The method outperforms state-of-the-art large-scale EEG models by an average of 4.57% in AUROC for few-shot emotion recognition and 11.92% in accuracy for zero-shot generalization to a new dataset .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-25</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.22197v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.22197.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>SentiMaithili: A Benchmark Dataset for Sentiment and Reason Generation for the Low-Resource Maithili Language</h3>
|
||||
<div class="layman-box">💡 This research presents techniques for language AI.</div>
|
||||
<div class="summary"> Maithili is an Indo-Aryan language spoken by more than 13 million people in the Purvanchal region of India . It is valued for its rich linguistic structure and cultural significance .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CL</span>
|
||||
<span class="date">2025-10-25</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.22160v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.22160.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects</h3>
|
||||
<div class="layman-box">💡 This research reduces computer vision.</div>
|
||||
<div class="summary"> Foundation models have transformed AI by reducing reliance on task-specific data through large-scale pretraining . While successful in language and vision, their adoption in EEG has lagged due to the heterogeneity of public datasets . Existing EEG foundation models struggle to generalize across these variations, often restricting pretraining to a single setup . We present REVE (Representation for EEG with Versatile Embeddings) a pretrained model .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-24</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.21585v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.21585.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
</div>
|
||||
</section>
|
||||
<section class="interest-section">
|
||||
<div class="interest-header">
|
||||
<span>🔬</span>
|
||||
<h2 class="interest-title">Lightweight Systems</h2>
|
||||
</div>
|
||||
<div class="papers-grid">
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Vectorized Context-Aware Embeddings for GAT-Based Collaborative Filtering</h3>
|
||||
<div class="layman-box">💡 This research enhances language AI.</div>
|
||||
<div class="summary"> Recommender systems often struggle with data sparsity and cold-start scenarios . This paper presents a Graph Attention Network (GAT) based Collaborative Filtering (CF) framework enhanced with context aware embeddings .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.IR</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26461v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26461.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟡 Advanced</span>
|
||||
</div>
|
||||
<h3>On neighborhoods of embedded toroidal and Hopf manifolds and their foliations</h3>
|
||||
<div class="layman-box">💡 This research running AI on low-power devices for edge computing.</div>
|
||||
<div class="summary"> In this article, we give completely new examples of embedded complex manifolds the germ of neighborhood of which is holomorphically equivalent to the zero section in its normal bundle . The first set of examples is composed of connected abelian complex Lie groups, embedded in some complex manifold $M$. The second set is $n$-dimensional Hopf manifolds, embedded as hypersurfaces .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">math.CV</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26454v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26454.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings</h3>
|
||||
<div class="layman-box">💡 This research makes more efficient language AI.</div>
|
||||
<div class="summary"> The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks necessitates the creation of small yet representative data subsets that enable efficient assessment while retaining predictive fidelity . Current methods for this task operate under a model-centric paradigm, selecting benchmarking items based on the collective performance of existing models . Such approaches are limited by large upfront costs, an inability to immediately handle new benchmarks (`cold-start'), and the fragile assumption that future models will share the failure patterns of their predecessors .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.AI</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26384v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26384.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟡 Advanced</span>
|
||||
</div>
|
||||
<h3>From Embedding to Control: Representations for Stochastic Multi-Object Systems</h3>
|
||||
<div class="layman-box">💡 This research achieves better machine learning.</div>
|
||||
<div class="summary"> This paper studies how to achieve accurate modeling and effective control in stochastic nonlinear dynamics with multiple interacting objects . Non-uniform interactions and random topologies make this task challenging .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">eess.SY</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26344v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26344.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🔴 Theory-Heavy</span>
|
||||
</div>
|
||||
<h3>Sharp embeddings and existence results for Logarithmic $p$-Laplacian equations with critical growth</h3>
|
||||
<div class="layman-box">💡 This research explores techniques in machine learning.</div>
|
||||
<div class="summary"> In this paper, we derive a new $p$-Logarithmic Sobolev inequality and optimal continuous and compact embeddings into Orlicz-type spaces of the function space associated with the logarathmic $p$.-Laplacian . By employing the method of the Nehari manifold, we prove the existence of a nontrivial weak solution . We conduct an asymptotic analysis of a weighted nonlocal, nonlinear problem governed by the fractional</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">math.AP</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26286v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26286.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Accretion rates of stellar-mass compact objects embedded in AGN discs</h3>
|
||||
<div class="layman-box">💡 This research running AI on low-power devices for edge computing.</div>
|
||||
<div class="summary"> Stellar-mass compact objects (COs) embedded in active galactic nucleus (AGN) discs are commonly assumed to accrete via Bondi or Bondi-Hoyle-Lyttleton prescriptions . We show that differential rotation in AGN discs can impart non-negligible angular momentum, in which case accretion proceeds through a viscous disc rather than Bondi/BHL flow .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">astro-ph.HE</span>
|
||||
<span class="date">2025-10-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.26111v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.26111.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟡 Advanced</span>
|
||||
</div>
|
||||
<h3>An explicit formula of the limit of the heat kernel measures on the spheres embedded in $\R^\infty$</h3>
|
||||
<div class="layman-box">💡 This research explores techniques in machine learning.</div>
|
||||
<div class="summary"> We show that the heat kernel measures based at the north pole of the spheres converges to a Gaussian measure in $R^\infty$ We also find an explicit formula for this measure .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">math.PR</span>
|
||||
<span class="date">2025-10-29</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.25855v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.25855.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟡 Advanced</span>
|
||||
</div>
|
||||
<h3>Tight Spherical Embeddings (Updated Version)</h3>
|
||||
<div class="layman-box">💡 This research explores techniques in machine learning.</div>
|
||||
<div class="summary"> This is an updated version of a paper which appeared in the proceedings of the 1979 Berlin Colloquium on Global Differential Geometry . The main result of this paper is that every compact isoparametric hypersurface $M^n \subset S^{n+1} is tight .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">math.DG</span>
|
||||
<span class="date">2025-10-29</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.25611v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.25611.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Enhanced quality factors at resonance in acoustofluidic cavities embedded in matched elastic metamaterials</h3>
|
||||
<div class="layman-box">💡 This research enhances machine learning.</div>
|
||||
<div class="summary"> We show that by embedding liquid-filled acoustofluidic cavities in a metamaterial, the quality factor of the cavity at selected acoustic resonance modes can be enhanced by 2 to 3 orders of magnitude .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">physics.flu-dyn</span>
|
||||
<span class="date">2025-10-29</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.25527v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.25527.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Hierarchical Physics-Embedded Learning for Spatiotemporal Dynamical Systems</h3>
|
||||
<div class="layman-box">💡 This research explores techniques in edge computing.</div>
|
||||
<div class="summary"> Modeling complex spatiotemporal dynamics, particularly in far-from-equilibrium systems, remains a challenge in science . The governing partial differential equations (PDEs) for these systems are often intractable to derive from first principles .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.LG</span>
|
||||
<span class="date">2025-10-29</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.25306v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.25306.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
</div>
|
||||
</section>
|
||||
<section class="interest-section">
|
||||
<div class="interest-header">
|
||||
<span>🔬</span>
|
||||
<h2 class="interest-title">Offline-First / Local AI</h2>
|
||||
</div>
|
||||
<div class="papers-grid">
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypots</h3>
|
||||
<div class="layman-box">💡 This research explores techniques in language AI.</div>
|
||||
<div class="summary"> Honeypots are decoy systems used for gathering valuable threat intelligence . Maximising attacker engagement is essential to their utility . Research has highlighted that context-awareness is necessary to increase engagement . Large Language Models (LLMs) have been shown as one approach to increase context awareness .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CR</span>
|
||||
<span class="date">2025-10-24</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.21459v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.21459.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>REx86: A Local Large Language Model for Assisting in x86 Assembly Reverse Engineering</h3>
|
||||
<div class="layman-box">💡 This research improves language AI.</div>
|
||||
<div class="summary"> Large Language Models offer potential for improving RE efficiency through automated comprehension and commenting . Cloud-hosted, closed-weight models pose privacy and security risks and cannot be used in closed-network facilities . REx86 reduces test-set cross-entropy loss by 64.2% and improves semantic cosine similarity against ground truth by 20.3\% over its base model .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CR</span>
|
||||
<span class="date">2025-10-23</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.20975v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.20975.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs</h3>
|
||||
<div class="layman-box">💡 This research achieves better language AI.</div>
|
||||
<div class="summary"> Mobile agents rely on Large Language Models (LLMs) to plan and execute tasks on smartphone user interfaces . While cloud-based LLMs achieve high task accuracy, they require uploading the full UI state at every step . In contrast, local LLMs avoid UI uploads but suffer from limited capacity, resulting in lower task success rates . CORE comprises three key components: (1) layout-aware block partitioning, (2) Co-planning) and Co-decision-making .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CL</span>
|
||||
<span class="date">2025-10-17</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.15455v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.15455.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>LLM-guided Hierarchical Retrieval</h3>
|
||||
<div class="layman-box">💡 This research explores techniques in language AI.</div>
|
||||
<div class="summary"> Modern IR systems are increasingly tasked with answering complex, multi-faceted queries that require deep reasoning . We introduce LATTICE, a hierarchical retrieval framework that enables an LLM to reason over and navigate large corpora with logarithmic search complexity .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.IR</span>
|
||||
<span class="date">2025-10-15</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.13217v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.13217.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions</h3>
|
||||
<div class="layman-box">💡 This research enhances language AI.</div>
|
||||
<div class="summary"> COSTAR-A is a novel prompt engineering framework that enhances the existing COSTAR method . COSTAR stands for Context, Objective, Style, Tone, Audience, and Response, by adding the 'Answer' component at the end .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CL</span>
|
||||
<span class="date">2025-10-14</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.12637v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.12637.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Bridging Semantics & Structure for Software Vulnerability Detection using Hybrid Network Models</h3>
|
||||
<div class="layman-box">💡 This research explores techniques in language AI.</div>
|
||||
<div class="summary"> Software vulnerabilities remain a persistent risk, yet static and dynamic analyses often overlook structural dependencies that shape insecure behaviors . Viewing programs as heterogeneous graphs, we capture control- and data-flow relations as complex interaction networks . Our hybrid framework combines these graph representations with light-weight (<4B) local LLMs .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.SE</span>
|
||||
<span class="date">2025-10-11</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.10321v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.10321.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>Open WebUI: An Open, Extensible, and Usable Interface for AI Interaction</h3>
|
||||
<div class="layman-box">💡 This research presents techniques for language AI.</div>
|
||||
<div class="summary"> The toolkit is designed to be open (open-source and local), extensible ( plugin support and users can interact with multiple models) The extensibility is enabled through a two-pronged plugin architecture and a community platform for sharing, importing, and adapting extensions .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.HC</span>
|
||||
<span class="date">2025-10-02</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.02546v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.02546.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>DualTune: Decoupled Fine-Tuning for On-Device Agentic Systems</h3>
|
||||
<div class="layman-box">💡 This research protecting data privacy in language AI.</div>
|
||||
<div class="summary"> Large Language Models (LLMs) consistently underperform compared to frontier models in tool calling scenarios . We propose "decoupled fine-tuning" to create dedicated LoRA adapters for tool selection and tool-specific argument generation using separate loss masking for each of the subtasks . DualTune is an inference framework that leverages the LRA adapters created using decoupled fines-tune to perform efficient agent orchestration with the help of local models .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.AI</span>
|
||||
<span class="date">2025-09-30</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2510.00229v2" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2510.00229.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair</h3>
|
||||
<div class="layman-box">💡 This research automatically finding language AI.</div>
|
||||
<div class="summary"> Static analysis tools like Bandit are effective at vulnerability detection but suffer from high false positives and lack repair capabilities . Large Language Models (LLMs) can suggest fixes but often hallucinate changes and lack self-validation . We present SecureFixAgent, a hybrid repair framework integrating Bandit with lightweight local LLMs in an iterative detect-repair-validate loop .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.CR</span>
|
||||
<span class="date">2025-09-18</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2509.16275v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2509.16275.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
<article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">🟢 Applied</span>
|
||||
</div>
|
||||
<h3>PrivWeb: Unobtrusive and Content-aware Privacy Protection For Web Agents</h3>
|
||||
<div class="layman-box">💡 This research protecting data privacy in language AI.</div>
|
||||
<div class="summary"> PrivWeb is a trusted add-on on web agents that anonymizes private information on interfaces according to user preferences . It features privacy categorization and adaptive notifications that selectively pauses tasks for user control over information collection for highly sensitive information . PrivWeb reduces perceived privacy risks with no associated increase in cognitive effort, and resulted in higher overall satisfaction .</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">cs.HC</span>
|
||||
<span class="date">2025-09-15</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="http://arxiv.org/abs/2509.11939v1" target="_blank">Abstract ↗</a>
|
||||
<a href="https://arxiv.org/pdf/2509.11939.pdf" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
</div>
|
||||
</section>
|
||||
<div class="footer">
|
||||
✨ Generated automatically • Powered by arXiv API
|
||||
</div>
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
84
config.json
Normal file
84
config.json
Normal file
@@ -0,0 +1,84 @@
|
||||
{
|
||||
"interests": {
|
||||
"Efficient ML / Edge AI": {
|
||||
"query": "cat:cs.LG OR cat:cs.CV OR cat:cs.CL",
|
||||
"keywords": [
|
||||
"efficient",
|
||||
"edge",
|
||||
"compression",
|
||||
"quantization",
|
||||
"pruning",
|
||||
"distillation",
|
||||
"inference",
|
||||
"lightweight",
|
||||
"mobile",
|
||||
"accelerat"
|
||||
]
|
||||
},
|
||||
"Privacy-Preserving ML": {
|
||||
"query": "cat:cs.CR OR cat:cs.LG",
|
||||
"keywords": [
|
||||
"privacy",
|
||||
"federated",
|
||||
"differential",
|
||||
"secure",
|
||||
"encrypted",
|
||||
"confidential",
|
||||
"private",
|
||||
"anonymi"
|
||||
]
|
||||
},
|
||||
"Creative AI / Emotion": {
|
||||
"query": "cat:cs.AI OR cat:cs.SD OR cat:cs.HC",
|
||||
"keywords": [
|
||||
"emotion",
|
||||
"generative",
|
||||
"creative",
|
||||
"music",
|
||||
"affective",
|
||||
"sentiment",
|
||||
"art",
|
||||
"design",
|
||||
"audio",
|
||||
"synthesis"
|
||||
]
|
||||
},
|
||||
"Lightweight Systems": {
|
||||
"query": "cat:cs.DC OR cat:cs.AR",
|
||||
"keywords": [
|
||||
"embedded",
|
||||
"iot",
|
||||
"edge",
|
||||
"resource",
|
||||
"constrained",
|
||||
"microcontroller",
|
||||
"low-power",
|
||||
"sensor",
|
||||
"device"
|
||||
]
|
||||
},
|
||||
"Offline-First / Local AI": {
|
||||
"query": "cat:cs.LG",
|
||||
"keywords": [
|
||||
"local",
|
||||
"device",
|
||||
"mobile",
|
||||
"offline",
|
||||
"on-device",
|
||||
"edge",
|
||||
"browser",
|
||||
"client-side",
|
||||
"standalone"
|
||||
]
|
||||
}
|
||||
},
|
||||
"settings": {
|
||||
"papers_per_interest": 10,
|
||||
"summary_max_length": 160,
|
||||
"recent_days": 7,
|
||||
"fallback_days": 90,
|
||||
"min_papers_threshold": 5,
|
||||
"fetch_multiplier": 5,
|
||||
"user_agent": "ResearchDigestBot/1.0 (github.com/wedsmoker)"
|
||||
}
|
||||
}
|
||||
BIN
desktop_demo.png
Normal file
BIN
desktop_demo.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 126 KiB |
205
generate_index.py
Normal file
205
generate_index.py
Normal file
@@ -0,0 +1,205 @@
|
||||
"""Generate an index.html page to browse all archived digests."""
|
||||
import os
|
||||
from datetime import datetime
|
||||
import glob
|
||||
|
||||
def generate_index():
|
||||
archive_dir = "arxiv_archive"
|
||||
|
||||
# Get all digest files
|
||||
if os.path.exists(archive_dir):
|
||||
digest_files = sorted(glob.glob(os.path.join(archive_dir, "arxiv_digest_*.html")), reverse=True)
|
||||
else:
|
||||
digest_files = []
|
||||
|
||||
# Parse dates and create entries
|
||||
entries = []
|
||||
for filepath in digest_files:
|
||||
filename = os.path.basename(filepath)
|
||||
# Extract date from filename: arxiv_digest_20251101.html
|
||||
date_str = filename.replace("arxiv_digest_", "").replace(".html", "")
|
||||
try:
|
||||
date_obj = datetime.strptime(date_str, "%Y%m%d")
|
||||
formatted_date = date_obj.strftime("%B %d, %Y")
|
||||
day_of_week = date_obj.strftime("%A")
|
||||
entries.append({
|
||||
'filename': filename,
|
||||
'date': formatted_date,
|
||||
'day': day_of_week,
|
||||
'date_obj': date_obj
|
||||
})
|
||||
except ValueError:
|
||||
continue
|
||||
|
||||
html = f"""<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>arXiv Digest Archive</title>
|
||||
<style>
|
||||
* {{ box-sizing: border-box; }}
|
||||
|
||||
body {{
|
||||
font-family: 'Inter', -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
|
||||
background: #0f0f0f;
|
||||
color: #e8e8e8;
|
||||
margin: 0;
|
||||
padding: 2rem;
|
||||
}}
|
||||
|
||||
.container {{
|
||||
max-width: 900px;
|
||||
margin: 0 auto;
|
||||
}}
|
||||
|
||||
header {{
|
||||
text-align: center;
|
||||
margin-bottom: 3rem;
|
||||
padding-bottom: 2rem;
|
||||
border-bottom: 2px solid #2a2a2a;
|
||||
}}
|
||||
|
||||
h1 {{
|
||||
font-weight: 900;
|
||||
font-size: 2.5rem;
|
||||
margin: 0 0 0.5rem 0;
|
||||
background: linear-gradient(135deg, #ff6b6b, #ffa94d);
|
||||
-webkit-background-clip: text;
|
||||
-webkit-text-fill-color: transparent;
|
||||
background-clip: text;
|
||||
}}
|
||||
|
||||
.subtitle {{
|
||||
color: #999;
|
||||
font-size: 1rem;
|
||||
}}
|
||||
|
||||
.latest-link {{
|
||||
display: inline-block;
|
||||
background: #ff6b6b;
|
||||
color: white;
|
||||
padding: 1rem 2rem;
|
||||
border-radius: 8px;
|
||||
text-decoration: none;
|
||||
font-weight: 700;
|
||||
margin-bottom: 3rem;
|
||||
transition: transform 0.2s, box-shadow 0.2s;
|
||||
}}
|
||||
|
||||
.latest-link:hover {{
|
||||
transform: translateY(-2px);
|
||||
box-shadow: 0 8px 24px rgba(255, 107, 107, 0.3);
|
||||
}}
|
||||
|
||||
.archive-list {{
|
||||
list-style: none;
|
||||
padding: 0;
|
||||
}}
|
||||
|
||||
.archive-item {{
|
||||
background: #1a1a1a;
|
||||
border: 1px solid #2a2a2a;
|
||||
border-radius: 10px;
|
||||
padding: 1.5rem;
|
||||
margin-bottom: 1rem;
|
||||
transition: all 0.2s;
|
||||
}}
|
||||
|
||||
.archive-item:hover {{
|
||||
border-color: #ff6b6b;
|
||||
transform: translateX(5px);
|
||||
}}
|
||||
|
||||
.archive-item a {{
|
||||
text-decoration: none;
|
||||
color: #e8e8e8;
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
}}
|
||||
|
||||
.date-info {{
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 0.3rem;
|
||||
}}
|
||||
|
||||
.date-main {{
|
||||
font-size: 1.2rem;
|
||||
font-weight: 700;
|
||||
color: #6ba3ff;
|
||||
}}
|
||||
|
||||
.date-day {{
|
||||
font-size: 0.9rem;
|
||||
color: #999;
|
||||
}}
|
||||
|
||||
.arrow {{
|
||||
font-size: 1.5rem;
|
||||
color: #ff6b6b;
|
||||
}}
|
||||
|
||||
.no-reports {{
|
||||
text-align: center;
|
||||
color: #999;
|
||||
padding: 3rem;
|
||||
}}
|
||||
|
||||
.stats {{
|
||||
text-align: center;
|
||||
margin-top: 3rem;
|
||||
padding-top: 2rem;
|
||||
border-top: 1px solid #2a2a2a;
|
||||
color: #999;
|
||||
font-size: 0.9rem;
|
||||
}}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div class="container">
|
||||
<header>
|
||||
<h1>📚 arXiv Digest Archive</h1>
|
||||
<p class="subtitle">Browse your daily research digests</p>
|
||||
</header>
|
||||
|
||||
<div style="text-align: center;">
|
||||
<a href="latest.html" class="latest-link">📰 View Latest Digest</a>
|
||||
</div>
|
||||
|
||||
<h2 style="margin-bottom: 1.5rem; color: #e8e8e8;">Past Reports</h2>
|
||||
"""
|
||||
|
||||
if entries:
|
||||
html += ' <ul class="archive-list">\n'
|
||||
for entry in entries:
|
||||
html += f""" <li class="archive-item">
|
||||
<a href="arxiv_archive/{entry['filename']}">
|
||||
<div class="date-info">
|
||||
<div class="date-main">{entry['date']}</div>
|
||||
<div class="date-day">{entry['day']}</div>
|
||||
</div>
|
||||
<div class="arrow">→</div>
|
||||
</a>
|
||||
</li>
|
||||
"""
|
||||
html += ' </ul>\n'
|
||||
else:
|
||||
html += ' <div class="no-reports">No archived reports yet. Run the digest script to generate your first report!</div>\n'
|
||||
|
||||
html += f"""
|
||||
<div class="stats">
|
||||
{len(entries)} report{"s" if len(entries) != 1 else ""} archived • Updated {datetime.now().strftime("%B %d, %Y at %I:%M %p")}
|
||||
</div>
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
"""
|
||||
|
||||
with open("index.html", 'w', encoding='utf-8') as f:
|
||||
f.write(html)
|
||||
print(f"📑 Index page generated with {len(entries)} reports")
|
||||
|
||||
if __name__ == "__main__":
|
||||
generate_index()
|
||||
512
generate_tiktok_feed.py
Normal file
512
generate_tiktok_feed.py
Normal file
@@ -0,0 +1,512 @@
|
||||
import json
|
||||
import random
|
||||
from datetime import datetime
|
||||
|
||||
def interleave_papers_by_interest(all_papers_by_interest):
|
||||
"""
|
||||
Interleave papers round-robin style across interests.
|
||||
Returns a flat list cycling through: Interest1[0], Interest2[0], ..., Interest1[1], Interest2[1], ...
|
||||
"""
|
||||
# Shuffle papers within each interest category
|
||||
for interest_name in all_papers_by_interest:
|
||||
random.shuffle(all_papers_by_interest[interest_name])
|
||||
|
||||
# Interleave round-robin
|
||||
interleaved = []
|
||||
interest_names = list(all_papers_by_interest.keys())
|
||||
max_papers = max(len(papers) for papers in all_papers_by_interest.values()) if all_papers_by_interest else 0
|
||||
|
||||
for i in range(max_papers):
|
||||
for interest_name in interest_names:
|
||||
papers = all_papers_by_interest[interest_name]
|
||||
if i < len(papers):
|
||||
# Add interest category to paper data
|
||||
papers[i]['interest_category'] = interest_name
|
||||
interleaved.append(papers[i])
|
||||
|
||||
return interleaved
|
||||
|
||||
def generate_tiktok_html(interleaved_papers):
|
||||
"""Generate self-contained TikTok-style feed HTML with embedded data."""
|
||||
|
||||
papers_json = json.dumps(interleaved_papers, indent=2, ensure_ascii=False)
|
||||
date_str = datetime.now().strftime('%B %d, %Y')
|
||||
|
||||
html = f"""<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=no"/>
|
||||
<title>Research Feed • {date_str}</title>
|
||||
<style>
|
||||
* {{
|
||||
box-sizing: border-box;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
}}
|
||||
|
||||
:root {{
|
||||
--bg: #000000;
|
||||
--text: #ffffff;
|
||||
--muted: #a0a0a0;
|
||||
--card-bg: #1a1a1a;
|
||||
--border: #2a2a2a;
|
||||
--accent: #ff6b6b;
|
||||
--heart-red: #ff4458;
|
||||
--layman-bg: #1f2937;
|
||||
--layman-border: #60a5fa;
|
||||
}}
|
||||
|
||||
body {{
|
||||
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
|
||||
background: var(--bg);
|
||||
color: var(--text);
|
||||
overflow-x: hidden;
|
||||
-webkit-font-smoothing: antialiased;
|
||||
}}
|
||||
|
||||
#feed-container {{
|
||||
height: 100vh;
|
||||
overflow-y: scroll;
|
||||
scroll-snap-type: y mandatory;
|
||||
-webkit-overflow-scrolling: touch;
|
||||
padding-top: 60px; /* Space for fixed header */
|
||||
}}
|
||||
|
||||
.paper-card {{
|
||||
min-height: 100vh;
|
||||
scroll-snap-align: start;
|
||||
scroll-snap-stop: always;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
justify-content: center;
|
||||
padding: 2rem 1.5rem;
|
||||
position: relative;
|
||||
border-bottom: 1px solid var(--border);
|
||||
}}
|
||||
|
||||
.interest-badge {{
|
||||
display: inline-block;
|
||||
background: var(--accent);
|
||||
color: white;
|
||||
padding: 0.4rem 0.9rem;
|
||||
border-radius: 20px;
|
||||
font-size: 0.7rem;
|
||||
font-weight: 700;
|
||||
text-transform: uppercase;
|
||||
letter-spacing: 0.5px;
|
||||
margin-bottom: 1rem;
|
||||
}}
|
||||
|
||||
.difficulty-badge {{
|
||||
display: inline-block;
|
||||
padding: 0.3rem 0.7rem;
|
||||
border-radius: 15px;
|
||||
font-size: 0.7rem;
|
||||
font-weight: 600;
|
||||
margin-left: 0.5rem;
|
||||
}}
|
||||
|
||||
.paper-title {{
|
||||
font-size: 1.5rem;
|
||||
font-weight: 800;
|
||||
line-height: 1.3;
|
||||
margin-bottom: 1rem;
|
||||
color: var(--text);
|
||||
}}
|
||||
|
||||
.layman-box {{
|
||||
background: var(--layman-bg);
|
||||
border-left: 3px solid var(--layman-border);
|
||||
padding: 1rem;
|
||||
margin-bottom: 1rem;
|
||||
border-radius: 8px;
|
||||
font-size: 0.95rem;
|
||||
line-height: 1.6;
|
||||
color: #94a3b8;
|
||||
font-style: italic;
|
||||
}}
|
||||
|
||||
.summary {{
|
||||
color: var(--muted);
|
||||
font-size: 0.95rem;
|
||||
line-height: 1.6;
|
||||
margin-bottom: 1.5rem;
|
||||
}}
|
||||
|
||||
.paper-meta {{
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
margin-bottom: 1rem;
|
||||
color: var(--muted);
|
||||
font-size: 0.8rem;
|
||||
}}
|
||||
|
||||
.category-tag {{
|
||||
background: #1e3a5f;
|
||||
color: #60a5fa;
|
||||
padding: 0.3rem 0.7rem;
|
||||
border-radius: 15px;
|
||||
font-size: 0.75rem;
|
||||
font-weight: 600;
|
||||
}}
|
||||
|
||||
.links {{
|
||||
display: flex;
|
||||
gap: 1.5rem;
|
||||
margin-bottom: 2rem;
|
||||
}}
|
||||
|
||||
.links a {{
|
||||
color: #6ba3ff;
|
||||
text-decoration: none;
|
||||
font-size: 0.9rem;
|
||||
font-weight: 600;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 0.3rem;
|
||||
}}
|
||||
|
||||
.links a:active {{
|
||||
color: var(--accent);
|
||||
}}
|
||||
|
||||
/* Fixed header with export button */
|
||||
.fixed-header {{
|
||||
position: fixed;
|
||||
top: 0;
|
||||
left: 0;
|
||||
right: 0;
|
||||
background: rgba(0, 0, 0, 0.95);
|
||||
backdrop-filter: blur(10px);
|
||||
padding: 0.8rem 1.5rem;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: space-between;
|
||||
border-bottom: 1px solid var(--border);
|
||||
z-index: 200;
|
||||
}}
|
||||
|
||||
.like-counter {{
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 0.5rem;
|
||||
color: var(--muted);
|
||||
font-size: 0.9rem;
|
||||
}}
|
||||
|
||||
.export-button {{
|
||||
background: linear-gradient(135deg, var(--accent), #ffa94d);
|
||||
color: white;
|
||||
border: none;
|
||||
padding: 0.6rem 1.2rem;
|
||||
border-radius: 20px;
|
||||
font-weight: 700;
|
||||
font-size: 0.85rem;
|
||||
cursor: pointer;
|
||||
transition: all 0.2s ease;
|
||||
-webkit-tap-highlight-color: transparent;
|
||||
opacity: 0.5;
|
||||
pointer-events: none;
|
||||
}}
|
||||
|
||||
.export-button.active {{
|
||||
opacity: 1;
|
||||
pointer-events: auto;
|
||||
}}
|
||||
|
||||
.export-button.active:active {{
|
||||
transform: scale(0.95);
|
||||
}}
|
||||
|
||||
.like-button {{
|
||||
position: fixed;
|
||||
bottom: 2rem;
|
||||
right: 1.5rem;
|
||||
width: 60px;
|
||||
height: 60px;
|
||||
border-radius: 50%;
|
||||
background: rgba(26, 26, 26, 0.9);
|
||||
border: 2px solid var(--border);
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
font-size: 1.8rem;
|
||||
cursor: pointer;
|
||||
transition: all 0.2s ease;
|
||||
z-index: 100;
|
||||
-webkit-tap-highlight-color: transparent;
|
||||
}}
|
||||
|
||||
.like-button:active {{
|
||||
transform: scale(0.9);
|
||||
}}
|
||||
|
||||
.like-button.liked {{
|
||||
background: var(--heart-red);
|
||||
border-color: var(--heart-red);
|
||||
animation: heartbeat 0.3s ease;
|
||||
}}
|
||||
|
||||
@keyframes heartbeat {{
|
||||
0%, 100% {{ transform: scale(1); }}
|
||||
50% {{ transform: scale(1.2); }}
|
||||
}}
|
||||
|
||||
.scroll-indicator {{
|
||||
position: fixed;
|
||||
bottom: 1rem;
|
||||
left: 50%;
|
||||
transform: translateX(-50%);
|
||||
color: var(--muted);
|
||||
font-size: 0.8rem;
|
||||
animation: bounce 2s infinite;
|
||||
z-index: 50;
|
||||
}}
|
||||
|
||||
@keyframes bounce {{
|
||||
0%, 100% {{ transform: translateX(-50%) translateY(0); }}
|
||||
50% {{ transform: translateX(-50%) translateY(-10px); }}
|
||||
}}
|
||||
|
||||
.hide-indicator {{
|
||||
display: none;
|
||||
}}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<!-- Fixed Header with Export Button -->
|
||||
<div class="fixed-header">
|
||||
<div class="like-counter">
|
||||
<span>♥</span>
|
||||
<span><span id="likeCount">0</span> liked</span>
|
||||
</div>
|
||||
<button class="export-button" id="exportButton">Export Likes</button>
|
||||
</div>
|
||||
|
||||
<div id="feed-container"></div>
|
||||
|
||||
<div class="like-button" id="likeButton">
|
||||
<span id="heartIcon">♡</span>
|
||||
</div>
|
||||
|
||||
<div class="scroll-indicator" id="scrollIndicator">
|
||||
↓ Scroll to explore
|
||||
</div>
|
||||
|
||||
<script>
|
||||
// ============================================
|
||||
// EMBEDDED PAPERS DATA
|
||||
// ============================================
|
||||
const papers = {papers_json};
|
||||
|
||||
// ============================================
|
||||
// STATE MANAGEMENT
|
||||
// ============================================
|
||||
let likes = JSON.parse(localStorage.getItem('tiktok_likes') || '{{}}');
|
||||
let currentPaperIndex = 0;
|
||||
|
||||
// ============================================
|
||||
// RENDER FEED
|
||||
// ============================================
|
||||
function renderFeed() {{
|
||||
const container = document.getElementById('feed-container');
|
||||
|
||||
papers.forEach((paper, index) => {{
|
||||
const card = document.createElement('div');
|
||||
card.className = 'paper-card';
|
||||
card.dataset.index = index;
|
||||
|
||||
card.innerHTML = `
|
||||
<div class="interest-badge">${{paper.interest_category}}</div>
|
||||
<div class="difficulty-badge">${{paper.difficulty}}</div>
|
||||
|
||||
<h1 class="paper-title">${{paper.title}}</h1>
|
||||
|
||||
<div class="layman-box">💡 ${{paper.layman}}</div>
|
||||
|
||||
<div class="summary">${{paper.summary}}</div>
|
||||
|
||||
<div class="paper-meta">
|
||||
<span class="category-tag">${{paper.category}}</span>
|
||||
<span class="date">${{paper.published}}</span>
|
||||
</div>
|
||||
|
||||
<div class="links">
|
||||
<a href="${{paper.link}}" target="_blank">Abstract ↗</a>
|
||||
<a href="${{paper.pdf_link}}" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
`;
|
||||
|
||||
container.appendChild(card);
|
||||
}});
|
||||
}}
|
||||
|
||||
// ============================================
|
||||
// LIKE SYSTEM
|
||||
// ============================================
|
||||
function getCurrentPaper() {{
|
||||
const container = document.getElementById('feed-container');
|
||||
const scrollPos = container.scrollTop;
|
||||
const windowHeight = window.innerHeight;
|
||||
|
||||
// Find which paper is currently in view
|
||||
const cards = document.querySelectorAll('.paper-card');
|
||||
for (let i = 0; i < cards.length; i++) {{
|
||||
const rect = cards[i].getBoundingClientRect();
|
||||
if (rect.top >= -windowHeight/2 && rect.top < windowHeight/2) {{
|
||||
return i;
|
||||
}}
|
||||
}}
|
||||
return 0;
|
||||
}}
|
||||
|
||||
function toggleLike() {{
|
||||
const paperIndex = getCurrentPaper();
|
||||
const paper = papers[paperIndex];
|
||||
const arxivId = paper.arxiv_id;
|
||||
|
||||
const heartIcon = document.getElementById('heartIcon');
|
||||
const likeButton = document.getElementById('likeButton');
|
||||
|
||||
if (likes[arxivId]) {{
|
||||
// Unlike
|
||||
delete likes[arxivId];
|
||||
heartIcon.textContent = '♡';
|
||||
likeButton.classList.remove('liked');
|
||||
}} else {{
|
||||
// Like
|
||||
likes[arxivId] = {{
|
||||
arxiv_id: arxivId,
|
||||
title: paper.title,
|
||||
abstract_url: paper.link,
|
||||
category: paper.category,
|
||||
interest_category: paper.interest_category,
|
||||
liked_date: new Date().toISOString(),
|
||||
difficulty: paper.difficulty
|
||||
}};
|
||||
heartIcon.textContent = '♥';
|
||||
likeButton.classList.add('liked');
|
||||
}}
|
||||
|
||||
// Save to localStorage
|
||||
localStorage.setItem('tiktok_likes', JSON.stringify(likes));
|
||||
|
||||
// Update counter and export button
|
||||
updateCounter();
|
||||
updateExportButton();
|
||||
}}
|
||||
|
||||
function updateLikeButton() {{
|
||||
const paperIndex = getCurrentPaper();
|
||||
const paper = papers[paperIndex];
|
||||
const heartIcon = document.getElementById('heartIcon');
|
||||
const likeButton = document.getElementById('likeButton');
|
||||
|
||||
if (likes[paper.arxiv_id]) {{
|
||||
heartIcon.textContent = '♥';
|
||||
likeButton.classList.add('liked');
|
||||
}} else {{
|
||||
heartIcon.textContent = '♡';
|
||||
likeButton.classList.remove('liked');
|
||||
}}
|
||||
}}
|
||||
|
||||
function updateCounter() {{
|
||||
const count = Object.keys(likes).length;
|
||||
document.getElementById('likeCount').textContent = count;
|
||||
}}
|
||||
|
||||
function updateExportButton() {{
|
||||
const exportButton = document.getElementById('exportButton');
|
||||
if (Object.keys(likes).length > 0) {{
|
||||
exportButton.classList.add('active');
|
||||
}} else {{
|
||||
exportButton.classList.remove('active');
|
||||
}}
|
||||
}}
|
||||
|
||||
// ============================================
|
||||
// EXPORT LIKES
|
||||
// ============================================
|
||||
function exportLikes() {{
|
||||
const likedPapers = Object.values(likes);
|
||||
|
||||
// Calculate category preferences
|
||||
const preferences = {{}};
|
||||
likedPapers.forEach(paper => {{
|
||||
const cat = paper.interest_category;
|
||||
preferences[cat] = (preferences[cat] || 0) + 1;
|
||||
}});
|
||||
|
||||
const exportData = {{
|
||||
liked_papers: likedPapers,
|
||||
preferences: preferences,
|
||||
export_date: new Date().toISOString(),
|
||||
total_likes: likedPapers.length
|
||||
}};
|
||||
|
||||
const blob = new Blob([JSON.stringify(exportData, null, 2)], {{
|
||||
type: 'application/json'
|
||||
}});
|
||||
|
||||
const url = URL.createObjectURL(blob);
|
||||
const a = document.createElement('a');
|
||||
a.href = url;
|
||||
a.download = `arxiv_likes_${{new Date().toISOString().split('T')[0]}}.json`;
|
||||
document.body.appendChild(a);
|
||||
a.click();
|
||||
document.body.removeChild(a);
|
||||
URL.revokeObjectURL(url);
|
||||
}}
|
||||
|
||||
// ============================================
|
||||
// EVENT LISTENERS
|
||||
// ============================================
|
||||
document.getElementById('likeButton').addEventListener('click', toggleLike);
|
||||
document.getElementById('exportButton').addEventListener('click', exportLikes);
|
||||
|
||||
// Update like button when scrolling
|
||||
document.getElementById('feed-container').addEventListener('scroll', () => {{
|
||||
updateLikeButton();
|
||||
|
||||
// Hide scroll indicator after first scroll
|
||||
const scrollIndicator = document.getElementById('scrollIndicator');
|
||||
if (document.getElementById('feed-container').scrollTop > 50) {{
|
||||
scrollIndicator.classList.add('hide-indicator');
|
||||
}}
|
||||
}});
|
||||
|
||||
// ============================================
|
||||
// INITIALIZATION
|
||||
// ============================================
|
||||
renderFeed();
|
||||
updateLikeButton();
|
||||
updateCounter();
|
||||
updateExportButton();
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
"""
|
||||
|
||||
return html
|
||||
|
||||
def save_tiktok_feed(all_papers_by_interest, filename='tiktok_feed.html'):
|
||||
"""
|
||||
Generate and save TikTok-style feed from papers data.
|
||||
Called by main.py after fetching papers.
|
||||
"""
|
||||
# Interleave papers round-robin
|
||||
interleaved = interleave_papers_by_interest(all_papers_by_interest)
|
||||
print(f"\n🔄 Interleaved {len(interleaved)} papers across {len(all_papers_by_interest)} interests")
|
||||
|
||||
# Generate HTML
|
||||
html = generate_tiktok_html(interleaved)
|
||||
|
||||
# Save file
|
||||
with open(filename, 'w', encoding='utf-8') as f:
|
||||
f.write(html)
|
||||
|
||||
print(f"✨ TikTok feed saved to {filename}")
|
||||
print("📱 Sync with your phone and open in browser!")
|
||||
724
main.py
Normal file
724
main.py
Normal file
@@ -0,0 +1,724 @@
|
||||
import os
|
||||
import time
|
||||
import json
|
||||
import xml.etree.ElementTree as ET
|
||||
import requests
|
||||
from transformers import pipeline
|
||||
from datetime import datetime, timedelta
|
||||
from generate_tiktok_feed import save_tiktok_feed
|
||||
|
||||
# ======================
|
||||
# CONFIGURATION
|
||||
# ======================
|
||||
|
||||
def load_config():
|
||||
"""Load configuration from config.json file."""
|
||||
config_file = "config.json"
|
||||
|
||||
# Default configuration (fallback)
|
||||
default_config = {
|
||||
"interests": {
|
||||
"Efficient ML / Edge AI": {
|
||||
"query": 'cat:cs.LG OR cat:cs.CV OR cat:cs.CL',
|
||||
"keywords": ['efficient', 'edge', 'compression', 'quantization', 'pruning', 'distillation', 'inference', 'lightweight', 'mobile', 'accelerat']
|
||||
}
|
||||
},
|
||||
"settings": {
|
||||
"papers_per_interest": 10,
|
||||
"summary_max_length": 160,
|
||||
"recent_days": 7,
|
||||
"fallback_days": 90,
|
||||
"min_papers_threshold": 5,
|
||||
"fetch_multiplier": 5,
|
||||
"user_agent": "ResearchDigestBot/1.0 (github.com/wedsmoker)"
|
||||
}
|
||||
}
|
||||
|
||||
if os.path.exists(config_file):
|
||||
try:
|
||||
with open(config_file, 'r', encoding='utf-8') as f:
|
||||
config = json.load(f)
|
||||
print(f"✅ Loaded configuration from {config_file}")
|
||||
return config
|
||||
except Exception as e:
|
||||
print(f"⚠️ Error loading config file: {e}. Using defaults.")
|
||||
return default_config
|
||||
else:
|
||||
print(f"⚠️ {config_file} not found. Using default configuration.")
|
||||
return default_config
|
||||
|
||||
# Load configuration
|
||||
config = load_config()
|
||||
INTERESTS = config.get('interests', {})
|
||||
settings = config.get('settings', {})
|
||||
|
||||
PAPERS_PER_INTEREST = settings.get('papers_per_interest', 10)
|
||||
SUMMARY_MAX_LENGTH = settings.get('summary_max_length', 160)
|
||||
USER_AGENT = settings.get('user_agent', 'ResearchDigestBot/1.0')
|
||||
|
||||
# Date filtering: Only fetch papers from the last N days (set to 0 to disable)
|
||||
RECENT_DAYS = settings.get('recent_days', 7)
|
||||
FALLBACK_DAYS = settings.get('fallback_days', 90)
|
||||
MIN_PAPERS_THRESHOLD = settings.get('min_papers_threshold', 5)
|
||||
FETCH_MULTIPLIER = settings.get('fetch_multiplier', 5)
|
||||
|
||||
# Deduplication: Track papers we've already shown
|
||||
SEEN_PAPERS_FILE = "seen_papers.json"
|
||||
|
||||
# Initialize summarizer (optional)
|
||||
try:
|
||||
summarizer = pipeline(
|
||||
"summarization",
|
||||
model="sshleifer/distilbart-cnn-12-6",
|
||||
device=-1
|
||||
)
|
||||
except Exception as e:
|
||||
print(f"⚠️ Summarizer unavailable ({e}). Using raw abstracts.")
|
||||
summarizer = None
|
||||
|
||||
# ======================
|
||||
# DEDUPLICATION HELPERS
|
||||
# ======================
|
||||
|
||||
def load_seen_papers():
|
||||
"""Load the set of previously seen paper IDs."""
|
||||
if os.path.exists(SEEN_PAPERS_FILE):
|
||||
try:
|
||||
with open(SEEN_PAPERS_FILE, 'r') as f:
|
||||
data = json.load(f)
|
||||
return set(data.get('seen_ids', []))
|
||||
except Exception as e:
|
||||
print(f"⚠️ Error loading seen papers: {e}")
|
||||
return set()
|
||||
|
||||
def save_seen_papers(seen_ids):
|
||||
"""Save the set of seen paper IDs."""
|
||||
try:
|
||||
with open(SEEN_PAPERS_FILE, 'w') as f:
|
||||
json.dump({
|
||||
'seen_ids': list(seen_ids),
|
||||
'last_updated': datetime.now().isoformat()
|
||||
}, f, indent=2)
|
||||
except Exception as e:
|
||||
print(f"⚠️ Error saving seen papers: {e}")
|
||||
|
||||
def get_date_filter(days=None):
|
||||
"""Generate date filter for arXiv query (last N days)."""
|
||||
if days is None:
|
||||
days = RECENT_DAYS
|
||||
|
||||
if days <= 0:
|
||||
return ""
|
||||
|
||||
end_date = datetime.now()
|
||||
start_date = end_date - timedelta(days=days)
|
||||
|
||||
# arXiv date format: YYYYMMDD0000 to YYYYMMDD2359
|
||||
date_filter = f"submittedDate:[{start_date.strftime('%Y%m%d')}0000 TO {end_date.strftime('%Y%m%d')}2359]"
|
||||
return date_filter
|
||||
|
||||
# ======================
|
||||
# ARXIV FETCH & PARSE
|
||||
# ======================
|
||||
|
||||
def fetch_arxiv_papers(query, max_results=5, days_back=None):
|
||||
url = "http://export.arxiv.org/api/query"
|
||||
|
||||
# Add date filter if configured
|
||||
date_filter = get_date_filter(days_back)
|
||||
if date_filter:
|
||||
# Combine user query with date filter using AND
|
||||
query = f"({query}) AND {date_filter}"
|
||||
|
||||
params = {
|
||||
"search_query": query,
|
||||
"start": 0,
|
||||
"max_results": max_results,
|
||||
"sortBy": "submittedDate",
|
||||
"sortOrder": "descending"
|
||||
}
|
||||
headers = {"User-Agent": USER_AGENT}
|
||||
try:
|
||||
response = requests.get(url, params=params, headers=headers, timeout=20)
|
||||
response.raise_for_status()
|
||||
return response.text
|
||||
except Exception as e:
|
||||
print(f"❌ Error fetching query '{query}': {e}")
|
||||
return None
|
||||
|
||||
def parse_papers(xml_data):
|
||||
if not xml_data:
|
||||
return []
|
||||
try:
|
||||
root = ET.fromstring(xml_data)
|
||||
except ET.ParseError:
|
||||
return []
|
||||
|
||||
namespace = {'atom': 'http://www.w3.org/2005/Atom'}
|
||||
papers = []
|
||||
|
||||
for entry in root.findall('atom:entry', namespace):
|
||||
title_elem = entry.find('atom:title', namespace)
|
||||
summary_elem = entry.find('atom:summary', namespace)
|
||||
id_elem = entry.find('atom:id', namespace)
|
||||
published_elem = entry.find('atom:published', namespace)
|
||||
|
||||
if None in (title_elem, summary_elem, id_elem):
|
||||
continue
|
||||
|
||||
title = ' '.join(title_elem.text.strip().split())
|
||||
summary = ' '.join(summary_elem.text.strip().split())
|
||||
link = id_elem.text
|
||||
published = published_elem.text.split('T')[0] if published_elem is not None else "Unknown"
|
||||
|
||||
# Extract arXiv ID
|
||||
arxiv_id = link.split('/abs/')[-1].split('v')[0]
|
||||
|
||||
# Get primary category
|
||||
primary_cat_elem = entry.find('.//{http://arxiv.org/schemas/atom}primary_category')
|
||||
category = primary_cat_elem.get('term') if primary_cat_elem is not None else "unknown"
|
||||
|
||||
papers.append({
|
||||
'title': title,
|
||||
'summary': summary,
|
||||
'link': link,
|
||||
'pdf_link': f"https://arxiv.org/pdf/{arxiv_id}.pdf",
|
||||
'arxiv_id': arxiv_id,
|
||||
'category': category,
|
||||
'published': published
|
||||
})
|
||||
return papers
|
||||
|
||||
def summarize_abstract(abstract):
|
||||
if summarizer is None:
|
||||
return abstract[:SUMMARY_MAX_LENGTH] + ("..." if len(abstract) > SUMMARY_MAX_LENGTH else "")
|
||||
try:
|
||||
if len(abstract.split()) < 15:
|
||||
return abstract
|
||||
result = summarizer(
|
||||
abstract,
|
||||
max_length=min(SUMMARY_MAX_LENGTH, 142),
|
||||
min_length=30,
|
||||
truncation=True
|
||||
)
|
||||
return result[0]['summary_text']
|
||||
except Exception as e:
|
||||
return abstract[:SUMMARY_MAX_LENGTH] + "..."
|
||||
|
||||
def calculate_relevance_score(paper, keywords):
|
||||
"""Calculate relevance score based on keyword matches in title and abstract."""
|
||||
title_lower = paper['title'].lower()
|
||||
abstract_lower = paper['summary'].lower()
|
||||
|
||||
score = 0
|
||||
matched_keywords = []
|
||||
|
||||
for keyword in keywords:
|
||||
keyword_lower = keyword.lower()
|
||||
# Title matches are worth more
|
||||
if keyword_lower in title_lower:
|
||||
score += 3
|
||||
matched_keywords.append(keyword)
|
||||
# Abstract matches
|
||||
elif keyword_lower in abstract_lower:
|
||||
score += 1
|
||||
matched_keywords.append(keyword)
|
||||
|
||||
# Bonus for multiple keyword matches
|
||||
if len(matched_keywords) > 2:
|
||||
score += len(matched_keywords) - 2
|
||||
|
||||
paper['relevance_score'] = score
|
||||
paper['matched_keywords'] = matched_keywords
|
||||
return score
|
||||
|
||||
def estimate_difficulty(abstract, category):
|
||||
"""Estimate paper difficulty using heuristic keyword analysis."""
|
||||
abstract_lower = abstract.lower()
|
||||
|
||||
# Theory-heavy indicators
|
||||
complexity_words = ['theoretical', 'proof', 'theorem', 'convergence', 'optimal',
|
||||
'asymptotic', 'lemma', 'proposition', 'rigorous', 'formalism']
|
||||
|
||||
# Applied/practical indicators
|
||||
applied_words = ['system', 'framework', 'application', 'dataset', 'benchmark',
|
||||
'implementation', 'experiment', 'empirical', 'practical']
|
||||
|
||||
# Math-heavy categories
|
||||
math_categories = ['math.', 'stat.', 'quant-ph']
|
||||
|
||||
# Calculate score
|
||||
score = sum(1 for w in complexity_words if w in abstract_lower)
|
||||
score -= sum(0.5 for w in applied_words if w in abstract_lower)
|
||||
|
||||
# Category bonus
|
||||
if any(cat in category for cat in math_categories):
|
||||
score += 1
|
||||
|
||||
# Determine difficulty level
|
||||
if score > 2:
|
||||
return "🔴 Theory-Heavy"
|
||||
elif score > 0.5:
|
||||
return "🟡 Advanced"
|
||||
else:
|
||||
return "🟢 Applied"
|
||||
|
||||
def generate_layman_context(title, abstract):
|
||||
"""Generate simple layman explanation using keyword extraction and templates."""
|
||||
abstract_lower = abstract.lower()
|
||||
|
||||
# Extract key action words and concepts
|
||||
action_map = {
|
||||
'improv': 'improves',
|
||||
'reduc': 'reduces',
|
||||
'enhanc': 'enhances',
|
||||
'optimi': 'optimizes',
|
||||
'acceler': 'speeds up',
|
||||
'efficient': 'makes more efficient',
|
||||
'novel': 'introduces a new approach to',
|
||||
'outperform': 'works better than existing methods for',
|
||||
'achiev': 'achieves better',
|
||||
'propose': 'proposes a method for',
|
||||
'present': 'presents techniques for',
|
||||
'address': 'tackles the problem of',
|
||||
'privacy': 'protecting data privacy in',
|
||||
'federated': 'distributed machine learning across',
|
||||
'emotion': 'understanding emotions in',
|
||||
'embedded': 'running AI on low-power devices for',
|
||||
'edge': 'running AI locally on devices for',
|
||||
'compression': 'making models smaller for',
|
||||
'inference': 'faster predictions in',
|
||||
'generative': 'creating new content with',
|
||||
'detection': 'automatically finding',
|
||||
'classification': 'categorizing',
|
||||
'prediction': 'forecasting'
|
||||
}
|
||||
|
||||
# Find first matching action
|
||||
action = "explores techniques in"
|
||||
for keyword, phrase in action_map.items():
|
||||
if keyword in abstract_lower[:300]: # Check first part of abstract
|
||||
action = phrase
|
||||
break
|
||||
|
||||
# Extract domain
|
||||
domain = "machine learning"
|
||||
if "language model" in abstract_lower or "llm" in abstract_lower or "nlp" in abstract_lower:
|
||||
domain = "language AI"
|
||||
elif "vision" in abstract_lower or "image" in abstract_lower or "visual" in abstract_lower:
|
||||
domain = "computer vision"
|
||||
elif "speech" in abstract_lower or "audio" in abstract_lower:
|
||||
domain = "speech processing"
|
||||
elif "privacy" in abstract_lower or "federated" in abstract_lower:
|
||||
domain = "privacy-preserving AI"
|
||||
elif "edge" in abstract_lower or "embedded" in abstract_lower or "device" in abstract_lower:
|
||||
domain = "edge computing"
|
||||
elif "emotion" in abstract_lower or "affective" in abstract_lower:
|
||||
domain = "emotion AI"
|
||||
|
||||
return f"This research {action} {domain}."
|
||||
|
||||
# ======================
|
||||
# HTML OUTPUT
|
||||
# ======================
|
||||
|
||||
def save_html_digest(all_papers_by_interest, filename=None):
|
||||
# Create archive directory if it doesn't exist
|
||||
archive_dir = "arxiv_archive"
|
||||
if not os.path.exists(archive_dir):
|
||||
os.makedirs(archive_dir)
|
||||
|
||||
if filename is None:
|
||||
date_str = datetime.now().strftime('%Y%m%d')
|
||||
filename = os.path.join(archive_dir, f"arxiv_digest_{date_str}.html")
|
||||
|
||||
# Also save as latest.html for easy syncing
|
||||
latest_file = "latest.html"
|
||||
|
||||
html = f"""<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
|
||||
<title>arXiv Digest • {datetime.now().strftime('%Y-%m-%d')}</title>
|
||||
<style>
|
||||
* {{ box-sizing: border-box; }}
|
||||
|
||||
:root {{
|
||||
--bg: #0f0f0f;
|
||||
--text: #e8e8e8;
|
||||
--muted: #999;
|
||||
--border: #2a2a2a;
|
||||
--card-bg: #1a1a1a;
|
||||
--link: #6ba3ff;
|
||||
--accent: #ff6b6b;
|
||||
--green: #51cf66;
|
||||
--yellow: #ffd43b;
|
||||
--red: #ff6b6b;
|
||||
--layman-bg: #1f2937;
|
||||
--layman-border: #60a5fa;
|
||||
}}
|
||||
|
||||
body {{
|
||||
font-family: 'Inter', -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
|
||||
line-height: 1.5;
|
||||
color: var(--text);
|
||||
background: var(--bg);
|
||||
margin: 0;
|
||||
padding: 1rem;
|
||||
}}
|
||||
|
||||
.container {{
|
||||
max-width: 1600px;
|
||||
margin: 0 auto;
|
||||
}}
|
||||
|
||||
header {{
|
||||
text-align: center;
|
||||
padding: 2rem 1rem 3rem;
|
||||
border-bottom: 2px solid var(--border);
|
||||
margin-bottom: 2rem;
|
||||
}}
|
||||
|
||||
h1 {{
|
||||
font-weight: 900;
|
||||
font-size: 2.5rem;
|
||||
margin: 0;
|
||||
background: linear-gradient(135deg, var(--accent), #ffa94d);
|
||||
-webkit-background-clip: text;
|
||||
-webkit-text-fill-color: transparent;
|
||||
background-clip: text;
|
||||
}}
|
||||
|
||||
.meta {{
|
||||
color: var(--muted);
|
||||
font-size: 0.95rem;
|
||||
margin-top: 0.5rem;
|
||||
letter-spacing: 0.5px;
|
||||
}}
|
||||
|
||||
.interest-section {{
|
||||
margin-bottom: 3rem;
|
||||
}}
|
||||
|
||||
.interest-header {{
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 0.8rem;
|
||||
margin-bottom: 1.2rem;
|
||||
padding: 0.8rem 1rem;
|
||||
background: var(--card-bg);
|
||||
border-radius: 12px;
|
||||
border-left: 4px solid var(--accent);
|
||||
}}
|
||||
|
||||
.interest-title {{
|
||||
font-size: 1.3rem;
|
||||
margin: 0;
|
||||
font-weight: 700;
|
||||
color: var(--text);
|
||||
}}
|
||||
|
||||
.papers-grid {{
|
||||
display: grid;
|
||||
grid-template-columns: repeat(auto-fill, minmax(380px, 1fr));
|
||||
gap: 1.2rem;
|
||||
}}
|
||||
|
||||
.paper {{
|
||||
background: var(--card-bg);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 12px;
|
||||
padding: 1.2rem;
|
||||
transition: all 0.2s ease;
|
||||
position: relative;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
height: 100%;
|
||||
}}
|
||||
|
||||
.paper:hover {{
|
||||
border-color: var(--accent);
|
||||
transform: translateY(-2px);
|
||||
box-shadow: 0 8px 24px rgba(255, 107, 107, 0.15);
|
||||
}}
|
||||
|
||||
.paper-header {{
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: flex-start;
|
||||
gap: 0.8rem;
|
||||
margin-bottom: 0.8rem;
|
||||
}}
|
||||
|
||||
.difficulty-badge {{
|
||||
padding: 0.3rem 0.7rem;
|
||||
border-radius: 20px;
|
||||
font-size: 0.7rem;
|
||||
font-weight: 700;
|
||||
white-space: nowrap;
|
||||
flex-shrink: 0;
|
||||
}}
|
||||
|
||||
.paper h3 {{
|
||||
font-size: 1.05rem;
|
||||
margin: 0 0 0.8rem 0;
|
||||
font-weight: 700;
|
||||
line-height: 1.4;
|
||||
color: var(--text);
|
||||
}}
|
||||
|
||||
.layman-box {{
|
||||
background: var(--layman-bg);
|
||||
border-left: 3px solid var(--layman-border);
|
||||
padding: 0.7rem 0.9rem;
|
||||
margin-bottom: 0.8rem;
|
||||
border-radius: 6px;
|
||||
font-size: 0.88rem;
|
||||
line-height: 1.5;
|
||||
color: #94a3b8;
|
||||
font-style: italic;
|
||||
}}
|
||||
|
||||
.summary {{
|
||||
color: var(--muted);
|
||||
margin-bottom: 1rem;
|
||||
font-size: 0.88rem;
|
||||
line-height: 1.6;
|
||||
flex-grow: 1;
|
||||
}}
|
||||
|
||||
.paper-footer {{
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
padding-top: 0.8rem;
|
||||
border-top: 1px solid var(--border);
|
||||
margin-top: auto;
|
||||
}}
|
||||
|
||||
.category-tag {{
|
||||
background: #1e3a5f;
|
||||
color: #60a5fa;
|
||||
padding: 0.25rem 0.65rem;
|
||||
border-radius: 15px;
|
||||
font-size: 0.75rem;
|
||||
font-weight: 600;
|
||||
}}
|
||||
|
||||
.date {{
|
||||
color: var(--muted);
|
||||
font-size: 0.75rem;
|
||||
}}
|
||||
|
||||
.links {{
|
||||
display: flex;
|
||||
gap: 1rem;
|
||||
margin-top: 0.8rem;
|
||||
}}
|
||||
|
||||
.links a {{
|
||||
color: var(--link);
|
||||
text-decoration: none;
|
||||
font-size: 0.85rem;
|
||||
font-weight: 600;
|
||||
transition: color 0.2s;
|
||||
}}
|
||||
|
||||
.links a:hover {{
|
||||
color: var(--accent);
|
||||
}}
|
||||
|
||||
.footer {{
|
||||
text-align: center;
|
||||
margin-top: 4rem;
|
||||
padding: 2rem;
|
||||
color: var(--muted);
|
||||
font-size: 0.85rem;
|
||||
border-top: 1px solid var(--border);
|
||||
}}
|
||||
|
||||
@media (max-width: 768px) {{
|
||||
.papers-grid {{
|
||||
grid-template-columns: 1fr;
|
||||
}}
|
||||
h1 {{
|
||||
font-size: 2rem;
|
||||
}}
|
||||
}}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div class="container">
|
||||
<header>
|
||||
<h1>arXiv Research Digest</h1>
|
||||
<div class="meta">{datetime.now().strftime('%B %d, %Y')} • {sum(len(p) for p in all_papers_by_interest.values())} papers across {len(all_papers_by_interest)} interests</div>
|
||||
</header>
|
||||
"""
|
||||
|
||||
for interest_name, papers in all_papers_by_interest.items():
|
||||
html += f"""<section class="interest-section">
|
||||
<div class="interest-header">
|
||||
<span>🔬</span>
|
||||
<h2 class="interest-title">{interest_name}</h2>
|
||||
</div>
|
||||
"""
|
||||
if not papers:
|
||||
html += ' <p>No recent papers found.</p>\n'
|
||||
else:
|
||||
html += ' <div class="papers-grid">\n'
|
||||
for paper in papers:
|
||||
html += f""" <article class="paper">
|
||||
<div class="paper-header">
|
||||
<span class="difficulty-badge">{paper['difficulty']}</span>
|
||||
</div>
|
||||
<h3>{paper['title']}</h3>
|
||||
<div class="layman-box">💡 {paper['layman']}</div>
|
||||
<div class="summary">{paper['summary']}</div>
|
||||
<div class="paper-footer">
|
||||
<span class="category-tag">{paper['category']}</span>
|
||||
<span class="date">{paper['published']}</span>
|
||||
</div>
|
||||
<div class="links">
|
||||
<a href="{paper['link']}" target="_blank">Abstract ↗</a>
|
||||
<a href="{paper['pdf_link']}" target="_blank">PDF ↗</a>
|
||||
</div>
|
||||
</article>
|
||||
"""
|
||||
html += ' </div>\n'
|
||||
html += "</section>\n"
|
||||
|
||||
html += """ <div class="footer">
|
||||
✨ Generated automatically • Powered by arXiv API
|
||||
</div>
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
"""
|
||||
# Save archived version
|
||||
with open(filename, 'w', encoding='utf-8') as f:
|
||||
f.write(html)
|
||||
print(f"✨ HTML digest saved to {filename}")
|
||||
|
||||
# Also save as latest.html for quick access
|
||||
with open(latest_file, 'w', encoding='utf-8') as f:
|
||||
f.write(html)
|
||||
print(f"📄 Latest digest saved to {latest_file}")
|
||||
|
||||
# ======================
|
||||
# MAIN EXECUTION
|
||||
# ======================
|
||||
|
||||
if __name__ == "__main__":
|
||||
# Load previously seen papers
|
||||
seen_papers = load_seen_papers()
|
||||
print(f"📋 Loaded {len(seen_papers)} previously seen papers")
|
||||
|
||||
if RECENT_DAYS > 0:
|
||||
print(f"📅 Fetching papers from last {RECENT_DAYS} days")
|
||||
else:
|
||||
print("📅 Fetching all available papers (no date filter)")
|
||||
|
||||
all_papers = {}
|
||||
new_papers_count = 0
|
||||
duplicate_count = 0
|
||||
|
||||
for interest_name, interest_config in INTERESTS.items():
|
||||
query = interest_config['query']
|
||||
keywords = interest_config['keywords']
|
||||
|
||||
print(f"\n🔍 Fetching papers for: {interest_name}")
|
||||
xml_data = fetch_arxiv_papers(query, PAPERS_PER_INTEREST * FETCH_MULTIPLIER) # Fetch more to filter
|
||||
papers = parse_papers(xml_data) if xml_data else []
|
||||
|
||||
print(f" → Found {len(papers)} papers")
|
||||
|
||||
# Filter out duplicates and calculate relevance
|
||||
fresh_papers = []
|
||||
for p in papers:
|
||||
if p['arxiv_id'] not in seen_papers:
|
||||
# Store original abstract for analysis
|
||||
original_abstract = p['summary']
|
||||
|
||||
# Calculate relevance score FIRST (before summarization)
|
||||
calculate_relevance_score(p, keywords)
|
||||
|
||||
# Estimate difficulty level (use ORIGINAL abstract before summarization)
|
||||
p['difficulty'] = estimate_difficulty(original_abstract, p['category'])
|
||||
|
||||
# Generate layman context (use ORIGINAL abstract for better keyword extraction)
|
||||
p['layman'] = generate_layman_context(p['title'], original_abstract)
|
||||
|
||||
# Generate summary (do this last to avoid losing original abstract)
|
||||
p['summary'] = summarize_abstract(original_abstract)
|
||||
|
||||
fresh_papers.append(p)
|
||||
else:
|
||||
duplicate_count += 1
|
||||
|
||||
# Sort by relevance score (highest first)
|
||||
fresh_papers.sort(key=lambda x: x['relevance_score'], reverse=True)
|
||||
|
||||
# Take top N papers
|
||||
top_papers = fresh_papers[:PAPERS_PER_INTEREST]
|
||||
|
||||
# Mark these papers as seen
|
||||
for p in top_papers:
|
||||
seen_papers.add(p['arxiv_id'])
|
||||
new_papers_count += 1
|
||||
|
||||
all_papers[interest_name] = top_papers
|
||||
print(f" ✨ {len(top_papers)} new papers (from {len(fresh_papers)} candidates, skipped {len(papers) - len(fresh_papers)} duplicates)")
|
||||
if top_papers:
|
||||
print(f" 📊 Relevance scores: {[p['relevance_score'] for p in top_papers]}")
|
||||
|
||||
# FALLBACK: If we didn't get enough papers, try wider date range (only 1 extra request)
|
||||
if len(top_papers) < MIN_PAPERS_THRESHOLD and FALLBACK_DAYS > RECENT_DAYS:
|
||||
print(f" 🔄 Low yield, trying fallback search (last {FALLBACK_DAYS} days)...")
|
||||
time.sleep(3) # Respect rate limit before fallback request
|
||||
|
||||
xml_data_fallback = fetch_arxiv_papers(query, PAPERS_PER_INTEREST * FETCH_MULTIPLIER, days_back=FALLBACK_DAYS)
|
||||
papers_fallback = parse_papers(xml_data_fallback) if xml_data_fallback else []
|
||||
|
||||
print(f" → Found {len(papers_fallback)} papers in fallback")
|
||||
|
||||
# Process fallback papers
|
||||
fallback_fresh = []
|
||||
for p in papers_fallback:
|
||||
if p['arxiv_id'] not in seen_papers:
|
||||
original_abstract = p['summary']
|
||||
calculate_relevance_score(p, keywords)
|
||||
p['difficulty'] = estimate_difficulty(original_abstract, p['category'])
|
||||
p['layman'] = generate_layman_context(p['title'], original_abstract)
|
||||
p['summary'] = summarize_abstract(original_abstract)
|
||||
fallback_fresh.append(p)
|
||||
|
||||
# Sort fallback papers by relevance
|
||||
fallback_fresh.sort(key=lambda x: x['relevance_score'], reverse=True)
|
||||
|
||||
# Add top fallback papers to fill quota
|
||||
needed = PAPERS_PER_INTEREST - len(top_papers)
|
||||
additional_papers = fallback_fresh[:needed]
|
||||
|
||||
for p in additional_papers:
|
||||
seen_papers.add(p['arxiv_id'])
|
||||
new_papers_count += 1
|
||||
|
||||
top_papers.extend(additional_papers)
|
||||
all_papers[interest_name] = top_papers
|
||||
print(f" ✨ After fallback: {len(top_papers)} total papers")
|
||||
|
||||
# Be kind: 3-second delay between queries (arXiv recommendation)
|
||||
time.sleep(3)
|
||||
|
||||
# Save updated seen papers
|
||||
save_seen_papers(seen_papers)
|
||||
|
||||
print(f"\n📊 Summary:")
|
||||
print(f" • Total new papers: {new_papers_count}")
|
||||
print(f" • Total duplicates skipped: {duplicate_count}")
|
||||
print(f" • Total tracked papers: {len(seen_papers)}")
|
||||
|
||||
save_html_digest(all_papers)
|
||||
save_tiktok_feed(all_papers)
|
||||
print("\n✅ Done! Open the HTML files in your browser.")
|
||||
BIN
mobile_demo.png
Normal file
BIN
mobile_demo.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 223 KiB |
4
requirements.txt
Normal file
4
requirements.txt
Normal file
@@ -0,0 +1,4 @@
|
||||
transformers==4.46.2
|
||||
torch==2.5.1
|
||||
torchvision==0.20.1
|
||||
requests==2.32.3
|
||||
17
reset_seen_papers.py
Normal file
17
reset_seen_papers.py
Normal file
@@ -0,0 +1,17 @@
|
||||
"""
|
||||
Reset the seen_papers.json file to start fresh.
|
||||
Run this if you want to see papers again that were previously shown.
|
||||
"""
|
||||
import os
|
||||
import json
|
||||
|
||||
SEEN_PAPERS_FILE = "seen_papers.json"
|
||||
|
||||
if os.path.exists(SEEN_PAPERS_FILE):
|
||||
# Backup old file
|
||||
backup_file = SEEN_PAPERS_FILE.replace('.json', '_backup.json')
|
||||
os.rename(SEEN_PAPERS_FILE, backup_file)
|
||||
print(f"✅ Backed up old file to {backup_file}")
|
||||
print(f"✅ Reset complete! Next run will show all papers as fresh.")
|
||||
else:
|
||||
print("ℹ️ No seen_papers.json file found. Nothing to reset.")
|
||||
50
run_digest.bat
Normal file
50
run_digest.bat
Normal file
@@ -0,0 +1,50 @@
|
||||
@echo off
|
||||
REM ArXiv Digest Runner - Sets up environment and runs the script
|
||||
cd /d "%~dp0"
|
||||
|
||||
REM Check if virtual environment exists
|
||||
if not exist "venv\" (
|
||||
echo Virtual environment not found. Creating one...
|
||||
python -m venv venv
|
||||
if errorlevel 1 (
|
||||
echo Error creating virtual environment!
|
||||
echo Make sure Python is installed and available in PATH.
|
||||
pause
|
||||
exit /b 1
|
||||
)
|
||||
echo Virtual environment created successfully.
|
||||
|
||||
echo Installing dependencies...
|
||||
call venv\Scripts\activate.bat
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements.txt
|
||||
if errorlevel 1 (
|
||||
echo Error installing dependencies!
|
||||
pause
|
||||
exit /b 1
|
||||
)
|
||||
echo Dependencies installed successfully.
|
||||
) else (
|
||||
call venv\Scripts\activate.bat
|
||||
)
|
||||
|
||||
echo Running arXiv digest...
|
||||
python main.py
|
||||
if errorlevel 1 (
|
||||
echo Error running main script!
|
||||
pause
|
||||
goto :end
|
||||
)
|
||||
|
||||
echo Generating index page...
|
||||
python generate_index.py
|
||||
if errorlevel 1 (
|
||||
echo Error generating index!
|
||||
pause
|
||||
goto :end
|
||||
)
|
||||
|
||||
echo Done! All files updated.
|
||||
pause
|
||||
:end
|
||||
deactivate
|
||||
1304
tiktok_feed.html
Normal file
1304
tiktok_feed.html
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user