4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation Paper • 2512.17012 • Published 8 days ago • 41
VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models Paper • 2511.07299 • Published Nov 10 • 5
Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in Paper • 2512.14273 • Published 10 days ago • 7
view article Article Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models 11 days ago • 99
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation Paper • 2511.09611 • Published Nov 12 • 68
TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control Paper • 2510.09561 • Published Oct 10 • 7