All Stories

  1. Crimson: Collaborative Parameter Updates for Efficient Pipeline Training of Large Language Models
  2. swKokkos: An Athread Backend for Enhanced Kokkos with the Sunway Heterogeneous Architecture
  3. NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
  4. Fate: Fa s s s sE sdge Inference of Mixture-of-Experts Models via Cross-Layer Gate
  5. CrossFS: Improving Cross-Domain File System Performance with CRDT-Based Metadata Synchronization
  6. Survey on Learning-based Dynamic Fault Localization: From Traditional Machine Learning to Large Language Models
  7. OBDD-NET: End-to-End Learning of Ordered Binary Decision Diagrams
  8. Test-Time Adaptation of Medical Vision-Language Models with Mixture of Modality Experts
  9. Are External Contributions Important to Project Productivity in Open Source Software? A Deep Insight based on Issue Entropy
  10. Looking Back to Move Forward: Unveiling the Mysteries of HBM Errors to Predict Future Failures
  11. Preference-Strength-Aware Self-Improving Alignment with Generative Preference Models
  12. K lotski : Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline
  13. Cut to the Chase: An Error-Oriented Approach to Detect Error-Handling Bugs
  14. ModelFoundry: A Tool for DNN Modularization and On-Demand Model Reuse Inspired by the Wisdom of Software Engineering
  15. Optimus: Warming Serverless ML Inference via Inter-Function Model Transformation
  16. Can Machine Learning Pipelines Be Better Configured?
  17. Mask Again: Masked Knowledge Distillation for Masked Video Modeling
  18. Fine-grained Key-Value Memory Enhanced Predictor for Video Representation Learning
  19. Two Sides of the Same Coin: Exploiting the Impact of Identifiers in Neural Code Comprehension
  20. Understanding and Detecting On-The-Fly Configuration Bugs
  21. Ginver: Generative Model Inversion Attacks Against Collaborative Inference
  22. Influential Global and Local Contexts Guided Trace Representation for Fault Localization
  23. Opportunities and Challenges in Repeated Revisions to Pull-Requests: An Empirical Study
  24. Reentrancy Vulnerability Detection and Localization: A Deep Learning Based Two-phase Approach
  25. de G raph CS: Embedding Variable-based Flow Graph for Neural Code Search
  26. NeuronFair
  27. A universal data augmentation approach for fault localization
  28. Bridging pre-trained models and downstream tasks for source code understanding
  29. Multi-intention-aware configuration selection for performance tuning
  30. Who, What, Why and How? Towards the Monetary Incentive in Crowd Collaboration: A Case Study of Github’s Sponsor Mechanism
  31. Detecting Adversarial Samples with Graph-Guided Testing
  32. CP-detector
  33. An Empirical Study of Multi-discussing Pattern in Open-Source Software Development
  34. BugSum
  35. On the Shoulders of Giants
  36. Software visualization and deep transfer learning for effective software defect prediction
  37. Transferring Well-Trained Models for Cross-Project Issue Classification
  38. Who Will Become a Long-Term Contributor?
  39. A dataset of duplicate pull-requests in github
  40. Detecting Duplicate Pull-requests in GitHub