YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction Paper • 2611.05280 • Published 6 days ago • 33
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory Paper • 2610.40614 • Published 11 days ago • 48
MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation Paper • 2610.41104 • Published 10 days ago • 23
GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling Paper • 2610.37257 • Published 9 days ago • 38
PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations Paper • 2611.04870 • Published 6 days ago • 11
Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement Paper • 2610.40191 • Published 10 days ago • 79
WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining Paper • 2610.39278 • Published 11 days ago • 7
BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion Paper • 2610.41574 • Published 10 days ago • 11
WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training Paper • 2610.37161 • Published 13 days ago • 41
MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model Paper • 2610.37175 • Published 13 days ago • 7
HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience Paper • 2610.34186 • Published 15 days ago • 5
TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving Paper • 2610.37230 • Published 13 days ago • 26
UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents Paper • 2610.30932 • Published 18 days ago • 56
Dual Exam: Controlled Evaluation of Multimodal Agents and World Models Paper • 2610.31066 • Published 18 days ago • 25
Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents Paper • 2610.11942 • Published Oct 8 • 9