← authors · overview

• Nearest Neighbor Multivariate Time Series Forecasting
  2025 · 8 citations
• ACECODER: Acing Coder RL via Automated Test-Case Synthesis
  2025 · 3 citations
• RewardHarness: Self-Evolving Agentic Post-Training
  2026
• SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
  2026
• GraphDancer: Training LLMs to Explore and Reason over Graphs via Curriculum Reinforcement Learning
  2026
• VisCoder2: Building Multi-Language Visualization Coding Agents
  2025
• VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
  2025
• VideoScore2: Think before You Score in Generative Video Evaluation
  2025
• EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
  2025
• Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
  2025
• Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
  2025
• VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation
  2025
• VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search
  2025