Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Tools for Thought: Understanding, Protecting, and Augmenting Human Cognition with Generative AI—From Vision to ImplementationMicrosoft · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)Apr 13Sticky and Magnetic: Evaluating Error Correction and User Adaptation in Gaze and Pinch InteractionAlphabet · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)Apr 13IntentWeave: A Progressive Entry Ladder for Multi-Surface Browser Agents in Cloud PortalsAlibaba · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)Apr 13The Perfection Paradox: From Architect to Curator in AI-Assisted API DesignAlphabet · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)Apr 13From Passive Consumption to Active Interaction: Exploring Interactive LLM Scaffolding to Support Learning EngagementMicrosoft · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)Apr 13Break the Window: Exploring Spatial Decomposition of Webpages in XRAlphabet · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)Apr 13Proscenium: Exploring Design Spaces of Layered Information Experience on a Large Dual-Layer Transparent DisplayMicrosoft · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)Apr 13Toward an Intrusion Detection System for a Virtualization Framework in Edge ComputingTechnology Innovation Institute · IEEE Wireless Communications and Networking ConferenceApr 13SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World RepositoriesAlphabet · International Workshop on Large Language Models for Code (LLM4Code)4 citationsApr 12CASCADE: LLM-powered JavaScript Deobfuscator at GoogleAlphabet · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)4 citationsApr 12Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise ParallelismAlibaba · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)3 citationsApr 12WhatsCode: Large-Scale GenAI Deployment for Developer Efficiency at WhatsAppMeta · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)3 citationsApr 12Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in MicroservicesAlibaba · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)2 citationsApr 12Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program RepairAlphabet, Meta · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)2 citationsApr 12The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of ReasonMicrosoft · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)2 citationsApr 12An Eye for AI: Eye-Tracking the Micro-Interruptions of GenAI Code SuggestionsAlphabet · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)1 citationApr 12PosEyeDOM: Lightweight Positional Copilot Suggestion Logger for Eye-Tracking Applications using the DOMAlphabet · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)1 citationApr 12When LLMs Listen to Experts: Accurate Failure Diagnosis in Operating SystemsAlibaba · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)1 citationApr 12Intelligent Triage: Interpretable Incident Triage Workflow using LLM Extracted Triage ReasoningMicrosoft · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)1 citationApr 12AI Where It Matters: Where, Why, and How Developers Want AI Support in Daily WorkMicrosoft · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)1 citationApr 12PerfBench: Can Agents Resolve Real-World Performance Bugs?Microsoft · International Workshop on Agentic Engineering1 citationApr 12Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence RecommendationMeta · International World Wide Web Conference (WWW)1 citationApr 12MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior RecommendationiFlytek · International World Wide Web Conference (WWW)1 citationApr 12A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and ReflectionAlibaba · IEEE International Conference on Program Comprehension (ICPC)1 citationApr 12RuberDuckBench: A Benchmark for AI Coding AssistantsAlphabet, Meta · International Workshop on Large Language Models for Code (LLM4Code)1 citationApr 12