Trust-Region Behavior Blending for On-Policy Distillation Paper • 2605.31159 • Published 8 days ago • 64
Running Featured 24 Chasing the Counting Manifold in Open LLMs 📚 24 Counting manifolds in open LLMs from behavior to SAEs.
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare Paper • 2602.06717 • Published Feb 6 • 75
T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground Paper • 2512.10430 • Published Dec 11, 2025 • 119
ESSA: Evolutionary Strategies for Scalable Alignment Paper • 2507.04453 • Published Jul 6, 2025 • 5
ESSA: Evolutionary Strategies for Scalable Alignment Paper • 2507.04453 • Published Jul 6, 2025 • 5
Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success Paper • 2508.04280 • Published Aug 6, 2025 • 35