Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization Paper • 2607.10169 • Published Jul 11 • 14
Spectral Rewiring for Exploration, Purification, and Model Merging Paper • 2607.03065 • Published Jul 3 • 22
Weak-to-Strong Generalization via Direct On-Policy Distillation Paper • 2607.05394 • Published Jul 8 • 144
RedAct: Redacting Agent Capability Traces for Procedural Skill Protection Paper • 2606.10813 • Published Jun 10 • 25
FLEX: Continuous Agent Evolution via Forward Learning from Experience Paper • 2511.06449 • Published Nov 9, 2025 • 14
Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference Paper • 2508.02193 • Published Aug 4, 2025 • 139
Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers Paper • 2506.07986 • Published Jun 9, 2025 • 19
