| Tag | Title | Year | URL |
|---|---|---|---|
| Perception Encoder: The best visual embeddings are not at the output of the network | 2025 | url | |
| VLM | PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding | 2025 | url |
| Improving the Scaling Laws of Synthetic Data with Deliberate Practice | 2025 | ||
| Mission Impossible: A Statistical Perspective on Jailbreaking LLMs | 2024 | ||
| Multi-Token Attention | 2025 |