Fan Yang

TileLang: Bridge Programmability and Performance in Modern Neural Kernels

LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts

Sparse Attention Adaptation for Long Reasoning

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

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

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

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Automated Proof Generation for Rust Code via Self-Evolution

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

Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning

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

Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs