DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation Paper • 2607.05147 • Published 24 days ago • 39
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning Paper • 2607.07508 • Published 22 days ago • 26
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence Paper • 2606.19348 • Published Apr 26 • 16
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling Paper • 2606.13473 • Published Jun 11 • 93