Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs Paper • 2507.07990 • Published Jul 10 • 45
UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations Paper • 2505.08787 • Published May 13 • 14
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks Paper • 2501.08326 • Published Jan 14 • 33
