Token-Efficient Long Video Understanding for Multimodal LLMs Paper • 2503.04130 • Published 11 days ago • 80
Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction Paper • 2501.03218 • Published Jan 6 • 36
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization Paper • 2412.18525 • Published Dec 24, 2024 • 75
MarDini: Masked Autoregressive Diffusion for Video Generation at Scale Paper • 2410.20280 • Published Oct 26, 2024 • 23