VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding Paper • 2611.08449 • Published 2 days ago • 97
WeLM-Image: A Unified Image Generation Model towards Visual Intelligence Paper • 2611.07392 • Published 2 days ago • 42
FrontierPhysics: Evaluating Agents for End-to-End Physics Research Paper • 2611.06910 • Published 3 days ago • 55
MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model Paper • 2610.37175 • Published 11 days ago • 7
DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model Paper • 2610.31734 • Published 16 days ago • 19
HoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training Paper • 2610.32909 • Published 15 days ago • 4
Foundation4D: Towards a unified perception and reconstruction model for autonomous vehicles Paper • 2610.30340 • Published 17 days ago • 13
Reading, Writing, Sharing, and Interacting with the World through Video Paper • 2610.31668 • Published 16 days ago • 43
Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds Paper • 2610.27999 • Published 18 days ago • 98
MA-Bench: Measuring Operational Planning in Language Models Paper • 2610.19138 • Published 25 days ago • 6
DistScene: Object-to-Scene Distillation for 3D Scene Generation Paper • 2610.06960 • Published Oct 3 • 11
EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation Paper • 2610.07969 • Published Oct 6 • 13
VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning Paper • 2610.08761 • Published Oct 6 • 7
Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction Paper • 2610.04137 • Published Oct 2 • 11
EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling Paper • 2610.02298 • Published Oct 1 • 16