WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published 5 days ago • 54
WorldOlympiad: Can Your World Model Survive a Triathlon? Paper • 2606.11129 • Published 4 days ago • 29
WorldOlympiad: Can Your World Model Survive a Triathlon? Paper • 2606.11129 • Published 4 days ago • 29
MMAE: A Massive Multitask Audio Editing Benchmark Paper • 2606.07229 • Published 8 days ago • 44
Cosmos 3: Omnimodal World Models for Physical AI Paper • 2606.02800 • Published 12 days ago • 118
Streaming Communication in Multi-Agent Reasoning Paper • 2606.05158 • Published 10 days ago • 29
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding Paper • 2605.27365 • Published 18 days ago • 139
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction Paper • 2605.26115 • Published 19 days ago • 52
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction Paper • 2605.26115 • Published 19 days ago • 52
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction Paper • 2605.26115 • Published 19 days ago • 52
FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Paper • 2605.09430 • Published May 10
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization Paper • 2605.15980 • Published 29 days ago • 36