Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
A Prime-Generated Formalization of Nagata's Factoriality Theorem in Lean 4Microsoft · arXiv (Cornell University)Apr 6Justified or Just Convincing? Error Verifiability as a Dimension of LLM QualityMicrosoft · arXiv (Cornell University)Apr 6Context is All You NeedMicrosoft · arXiv (Cornell University)Apr 6Learning from Equivalence Queries, RevisitedAlphabet · arXiv (Cornell University)Apr 6Benchmarks and methods for 3D medical image retrievalMicrosoft · Scientific ReportsApr 6Scalable Gaussian process regression via median posterior inference for estimating the health effects of an environmental mixtureAlphabet · Biometrics2 citationsApr 5The Art of Building Verifiers for Computer Use AgentsMicrosoft · arXiv (Cornell University)Apr 5Beyond Fluency: Toward Reliable Trajectories in Agentic IRAlphabet · arXiv (Cornell University)Apr 5MagicCopy: Bring my data along with me beyond boundaries of appsMicrosoft · arXiv (Cornell University)Apr 5Rethinking Bitrate Adaptation in WebRTC-Based Low-Latency Live Streaming SystemsAlibaba · International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV)Apr 4Sovereign Cloud Buildout Using Repeatable and Scalable PatternsMicrosoft · Computer Fraud & SecurityApr 4Comparative Analysis of RAG Algorithms and LLM Fine-Tuning Methods for Domain-Specific Search TasksAlphabet · The American Journal of Engineering And TechnologyApr 4In search of truth: evaluating concordance of AI-based anatomy segmentation modelsNVIDIA · Journal of medical imaging1 citationApr 3Generative AI for Video Trailer Synthesis: From Extractive Heuristics to Autoregressive CreativityAlphabet · arXiv (Cornell University)Apr 3VisionClaw: Always-On AI Agents through Smart GlassesAlphabet · arXiv (Cornell University)Apr 3Are Arabic Benchmarks Reliable? QIMMA's Quality-First Approach to LLM EvaluationTechnology Innovation Institute · arXiv (Cornell University)Apr 3Towards Better Aligned LLM Judges for Radiology Report Evaluation across Modalities and AnatomiesMicrosoft · arXiv (Cornell University)Apr 3Olmo Hybrid: From Theory to Practice and BackAllen Institute for AI · arXiv (Cornell University)Apr 3The Tool Illusion: Rethinking Tool Use in Web AgentsMicrosoft · arXiv (Cornell University)Apr 3StoryScope: Investigating idiosyncrasies in AI fictionAlphabet · arXiv (Cornell University)Apr 3R2-Write: Reflection and Revision for Open-Ended Writing with Deep ReasoningAlibaba · arXiv (Cornell University)Apr 3AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use AgentsAlibaba · arXiv (Cornell University)Apr 3Deduplication can Make File Systems FasterAlibaba · ACM Transactions on StorageApr 3Context-Aware TFL: A Universal Context-Aware Contrastive Learning Framework for Temporal Forgery LocalizationAlibaba · IEEE Transactions on Dependable and Secure ComputingApr 3Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache ManagementAlibaba · Proceedings of the ACM on Management of Data3 citationsApr 2