Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos Paper • 2501.04001 • Published 9 days ago • 40
An Empirical Study of Autoregressive Pre-training from Videos Paper • 2501.05453 • Published 7 days ago • 35
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following Paper • 2501.08187 • Published 2 days ago • 24
Enhancing Automated Interpretability with Output-Centric Feature Descriptions Paper • 2501.08319 • Published 2 days ago • 10