How Synthetic Labels Improve Conformal Prediction: A Perspective on Conditional CoverageResearchSep 29, 2026
Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement LearningResearchSep 29, 2026
How to Tame a Multi-Headed Hydra? Adaptive Multi-Category Safety Steering for Large Language ModelsResearchSep 29, 2026
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual EvidenceResearchSep 29, 2026
Just Initialize: A Training-Free Initialization Component for Large-Scale Routing OptimizationResearchSep 29, 2026
Hamiltonian JEPA: Action-Conditioned World Models with an Inherited Control StateResearchSep 29, 2026