Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
What's DAT? Three Case Studies of Measuring Software Development Productivity at Meta With Diff Authoring TimeMeta · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)1 citationApr 12The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship AttributionTechnology Innovation Institute · International Workshop on Large Language Models for Code (LLM4Code)1 citationApr 12Product Manager Practices for Delegating Work to Generative AI: “Accountability must not be delegated to non-human actors”Microsoft · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)1 citationApr 12Smart Paste: Automatically Fixing Copy/Paste for Google DevelopersAlphabet · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)1 citationApr 12Enabling Black-box RPC-API Testing with Multi-Agent Reinforcement Learning and LLMs: An Industry Case StudyAlibaba · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)Apr 12LLM-Based Automated Diagnosis Of Integration Test Failures At GoogleAlphabet · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)Apr 12Achieving Productivity Gains with AI-based IDE features: A Journey at GoogleAlphabet, Meta · International Workshop on Large Language Models for Code (LLM4Code)Apr 12S 2 CDR: Smoothing-Sharpening Process Model for Cross-Domain RecommendationAlibaba · International World Wide Web Conference (WWW)Apr 12Additively Competitive SecretariesAlphabet · International World Wide Web Conference (WWW)Apr 12Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language ModelsLG AI Research · arXiv (Cornell University)Apr 12Replicable CompositionAlphabet · arXiv (Cornell University)Apr 12Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?Microsoft · arXiv (Cornell University)Apr 12Visual Enhanced Depth Scaling for Multimodal Latent ReasoningAlibaba · arXiv (Cornell University)Apr 12Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement LearningMicrosoft · arXiv (Cornell University)Apr 12CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-ExpertsCerebras Systems · arXiv (Cornell University)Apr 12A Causal Perspective on Measuring, Explaining and Mitigating Smells in LLM-Generated CodeMicrosoft · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)Apr 12Enabling Global, Human-Centered Explanations for LLMs: From Tokens to Interpretable Code and Test GenerationAlphabet, Microsoft · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)Apr 12Towards a Human-in-the-Loop Framework for Reliable Patch Evaluation Using an LLM-as-a-JudgeAlphabet · arXivApr 12Reading Between the Lines: Scalable User Feedback via Implicit Sentiment in Developer PromptsMeta · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)Apr 12Pathways of Thoughts: Multi-Directional Thinking for Long-form Personalized Question AnsweringAlphabet · International World Wide Web Conference (WWW)Apr 12Continuous Benchmark Generation for Evaluating Enterprise-scale LLM AgentsMicrosoft · International Workshop on Large Language Models for Code (LLM4Code)Apr 12Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent EvaluationMicrosoft · IEEE/ACM International Conference on AI Engineering – Software Engineering for AI (CAIN)Apr 12FreshBrew: A Benchmark for Evaluating AI Agents on Java Code MigrationAlphabet · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)Apr 12How to Strategize Human Content Creation in the Era of GenAI?Alphabet · International World Wide Web Conference (WWW)Apr 12From Searchable to Non-Searchable: Generative AI and Information Diversity in Online Information SeekingMicrosoft · arXiv (Cornell University)Apr 11