Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence? Paper • 2604.03016 • Published Apr 3 • 36
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models Paper • 2603.17051 • Published Mar 17 • 55
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG Paper • 2603.23497 • Published Mar 24 • 67
Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation Paper • 2603.18795 • Published Mar 19 • 17
VIDEOP2R: Video Understanding from Perception to Reasoning Paper • 2511.11113 • Published Nov 14, 2025 • 113
LRM: Large Reconstruction Model for Single Image to 3D Paper • 2311.04400 • Published Nov 8, 2023 • 48
