Running Agents 3 WorldArena 2.0 Leaderboard 🏆 3 Three-track leaderboard for embodied world model evaluation
Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System Paper • 2609.01607 • Published 7 days ago • 23
V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning Paper • 2608.25580 • Published 13 days ago • 16
AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling Paper • 2608.02602 • Published Aug 3 • 82
ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine Paper • 2607.28625 • Published Jul 30 • 46
Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence Paper • 2607.16401 • Published Jul 17 • 44
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence Paper • 2606.20515 • Published Jun 18 • 42
Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion Paper • 2606.15236 • Published Jun 16 • 22
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models Paper • 2605.30263 • Published May 28 • 61
SpatialBench: Is Your Spatial Foundation Model an All-Round Player? Paper • 2605.27367 • Published May 26 • 74