Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos Paper • 2501.04001 • Published 3 days ago • 32
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token Paper • 2501.03895 • Published 3 days ago • 37
An Empirical Study of Autoregressive Pre-training from Videos Paper • 2501.05453 • Published about 21 hours ago • 14
