All Stories

  1. On the Diffusion of Test Smells in LLM-Generated Unit Tests
  2. Who Wrote This Patch? Toward Accountable Automated Program Repair
  3. The Watermark Paradox: How Provenance Verification Paves the Road to Camouflaged Backdoors
  4. SPECTRA: Specification-Oriented Static Analysis for Smart Contract Security and Behavioral Contract Inference
  5. WasmCert: A Reproducible Hybrid Security Analysis Prototype for WebAssembly
  6. ConstantGuard: Lattice-Based Taint Analysis for Timing Side-Channel Risk Detection in C Code
  7. Just-in-Time Detection of Silent Security Patches
  8. RETHiNK: Simulating Human Reasoning via Multi-LLM Debate for Cognitive Reframing of Negative Thoughts
  9. You Don’t Have to Say Where to Edit! jLED—Joint Learning to Localize and Edit Source Code
  10. Hedgecode: A Multi-Task Hedging Contrastive Learning Framework for Code Search
  11. DataRecipe --- How to Cook the Data for CodeLLM?
  12. Learning to Represent Patches
  13. Enhancing Text-to-SQL Translation for Financial System Design
  14. Practical Program Repair via Preference-based Ensemble Strategy
  15. LGFat-RGCN: Faster Attention with Heterogeneous RGCN for Medical ICD Coding Generation
  16. Delving into Commit-Issue Correlation to Enhance Commit Message Generation Models
  17. StandUp4NPR: Standardizing SetUp for Empirically Comparing Neural Program Repair Systems
  18. Is this Change the Answer to that Problem?
  19. Automated Program Repair tools that rely on deep learning techniques