TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times Paper • 2512.16093 • Published 8 days ago • 62
LongVideoAgent: Multi-Agent Reasoning with Long Videos Paper • 2512.20618 • Published 3 days ago • 47
Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding Paper • 2512.17532 • Published 7 days ago • 62
N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models Paper • 2512.16561 • Published 8 days ago • 19
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration Paper • 2511.21689 • Published 30 days ago • 109
ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data Paper • 2509.15221 • Published Sep 18 • 111
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models Paper • 2505.24864 • Published May 30 • 143