PPaperPicks

Binyuan Hui

22 papers at tracked venues · 18 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning
  2. Towards Better Correctness and Efficiency in Code Generation
  3. CodeArena: Evaluating and Aligning CodeLLMs on Human Preference
  4. DEEM: Diffusion models serve as the eyes of large language models for image perception
  5. Fine-Tuning Language Models with Collaborative and Semantic Experts
  6. IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web
  7. Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation
  8. NLP+Code: Code Intelligence in Language Models
  9. OLMoE: Open Mixture-of-Experts Language Models
  10. OpenHands: An Open Platform for AI Software Developers as Generalist Agents
  11. Parallel Scaling Law for Language Models
  12. Qwen2.5-xCoder: Multi-Agent Collaboration for Multilingual Code Instruction Tuning
  13. START: Self-taught Reasoner with Tools
  14. SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
  15. SWE-smith: Scaling Data for Software Engineering Agents
  16. Synthesizing Software Engineering Data in a Test-Driven Manner
  17. Turning the Tide: Repository-based Code Reflection
  18. Iterative Forward Tuning Boosts In-Context Learning in Language Models
  19. Lemur: Harmonizing Natural Language and Code for Language Agents
  20. OctoPack: Instruction Tuning Code Large Language Models
  21. One-Shot Learning as Instruction Data Prospector for Large Language Models
  22. Synthesizing Text-to-SQL Data from Weak and Strong LLMs