CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion Paper • 2606.30030 • Published 20 days ago • 7
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published 21 days ago • 167
To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair Paper • 2606.26978 • Published 24 days ago • 4
ViT-Up: Faithful Feature Upsampling for Vision Transformers Paper • 2606.14024 • Published Jun 12 • 9
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction Paper • 2605.23889 • Published May 22 • 4
SOD: Step-wise On-policy Distillation for Small Language Model Agents Paper • 2605.07725 • Published May 8 • 26
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196
Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models Paper • 2605.08472 • Published May 8 • 5