← authors · overview

• Stepcoder: Improve Code Generation With Reinforcement Learning From Compiler Feedback
  2024 · 88 citations
• LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models
  2025 · 2 citations
• LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening
  2026
• CL-bench: A Benchmark for Context Learning
  2026
• SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
  2026
• PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models
  2026
• Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
  2026
• Probing How Scalable Table Data Enhances General Long-Context Reasoning
  2026
• Pre-Trained Policy Discriminators are General Reward Models
  2025
• Intern-S1: A Scientific Multimodal Foundation Model
  2025
• UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation
  2023
• Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective
  2024
• RMB: Comprehensively Benchmarking Reward Models in LLM Alignment
  2024
• Secrets of RLHF in Large Language Models Part I: PPO
  2023
• Secrets of RLHF in Large Language Models Part II: Reward Modeling
  2024