Player-1: Learning to Play from Synthetic Experience Paper • 2610.20584 • Published 10 days ago • 351
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published 24 days ago • 58
ARCS: Towards Precise Text-to-SQL via Structured Disambiguation Paper • 2610.09396 • Published 17 days ago • 13
InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators Paper • 2610.13944 • Published 15 days ago • 28
EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents Paper • 2610.13021 • Published 15 days ago • 76
EVISKILL: Grounding Skill Evolution in Replayable Evidence Paper • 2610.05030 • Published 20 days ago • 55
World Editing: Intervening on Executable Worlds at Increasing Depth Paper • 2610.02331 • Published 23 days ago • 31
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning Paper • 2609.35767 • Published 26 days ago • 50
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling Paper • 2609.34981 • Published 25 days ago • 140
QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents Paper • 2609.33848 • Published 27 days ago • 51
Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms Paper • 2609.23658 • Published Sep 20 • 31
Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles Paper • 2609.22220 • Published Sep 2 • 7
Paint-Anything: Unified Any-Color Control for Image Generation and Editing Paper • 2609.20816 • Published Sep 17 • 57
Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network Paper • 2609.20633 • Published Sep 17 • 13
GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills Paper • 2609.21749 • Published Sep 18 • 20
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation Paper • 2609.20744 • Published Sep 17 • 54