The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published 14 days ago • 161
Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models Paper • 2605.26895 • Published May 26 • 22
Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency Paper • 2605.19008 • Published May 18 • 4
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining Paper • 2605.14747 • Published May 14 • 147
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization Paper • 2605.15980 • Published May 15 • 36