All Stories

  1. Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
  2. One Size Does Fit All: Exploring Model Fusion for Software Engineering Tasks
  3. Coding in a Bubble? Evaluating LLMs in Resolving Context Adaptation Bugs during Code Adaptation
  4. Beyond Functional Correctness: A Knowledge-Enhanced Iterative Framework for Generating Criteria-Compliant Code
  5. Fault Localization from the Semantic Code Search Perspective
  6. EMSEdit: Efficient Multi-Step Meta-Learning-based Model Editing
  7. Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection
  8. Identifying Knowledge Editing Types in Large Language Models
  9. MiSum: Multi-modality Heterogeneous Code Graph Learning for Multi-intent Binary Code Summarization
  10. Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering
  11. Learning Feasible Causal Algorithmic Recourse: A Prior Structural Knowledge Free Approach
  12. Don’t Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
  13. Divide-and-Conquer: Automating Code Revisions via Localization-and-Revision
  14. One Size Does Not Fit All: Multi-granularity Patch Generation for Better Automated Program Repair
  15. AutoRIC: Automated Neural Network Repairing Based on Constrained Optimization
  16. CAREER: Context-Aware API Recognition with Data Augmentation for API Knowledge Extraction
  17. When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
  18. Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning
  19. An Extensive Study on Adversarial Attack against Pre-trained Models of Code
  20. Natural Language to Code: How Far Are We?
  21. CCT5: A Code-Change-Oriented Pre-trained Model
  22. Two Birds with One Stone: Boosting Code Generation and Code Search via a Generative Adversarial Network
  23. Pre-Implementation Method Name Prediction for Object-Oriented Programming
  24. Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
  25. Reentrancy Vulnerability Detection and Localization: A Deep Learning Based Two-phase Approach
  26. Is this Change the Answer to that Problem?
  27. Context-Aware Code Change Embedding for Better Patch Correctness Assessment
  28. Fine-grained code-comment semantic interaction analysis
  29. Lightweight global and local contexts guided method name recommendation with prior knowledge
  30. Automated patch correctness assessment
  31. On the efficiency of test suite based program repair