Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 28 days ago • 431
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 237
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining Paper • 2605.14747 • Published May 14 • 147
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published May 13 • 274
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions Paper • 2605.10664 • Published May 11 • 9
PhyCo: Learning Controllable Physical Priors for Generative Motion Paper • 2604.28169 • Published Apr 30 • 13