Mao Yang

LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs

Sparse Attention Adaptation for Long Reasoning

Diagnosing with Insights: Structured Analysis of Agent Failures via Behavioral Abstractions

AnTKV: Anchor Token-Aware Ultra-Low-Bit Vector Quantization for KV Cache in Large Language Models

Post Hoc Neuro-Symbolic Verification on Instruction Following of Language Models

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solver

LongRoPE2: Near-Lossless LLM Context Window Scaling

rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset

SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs