Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Syntactic Implicit Parameters with Static OverloadingMicrosoft · Proceedings of the ACM on Programming LanguagesJun 8Compiling Strassen-like Matrix Multiplication Algorithms to Fast CUDA KernelsMicrosoft · Proceedings of the ACM on Programming LanguagesJun 8SuperCollider: Scalable and Effective Data Race Detection for CUDANVIDIA · Proceedings of the ACM on Programming LanguagesJun 8HybridSkipList+: Rethinking Distributed Skiplist With Hybrid RDMA and CachingAlibaba · IEEE Transactions on ComputersJun 8RASO: Role-Aware Shared Reflection for Multi-Agent Orchestration in E-Commerce Long-Horizon PlanningAlibaba · Proceedings of the International Conference on Automated Planning and SchedulingJun 8Analyzing Bytes: Pre-Disassembly Static Binary AnalysisAlphabet · Proceedings of the ACM on Programming LanguagesJun 8TQR : Modelling user temporal preference for effective question routingAlibaba · Neural NetworksJun 8EREQ: Regular Expressions with Quantifiers and Incremental Quantifier EliminationMicrosoft · Proceedings of the ACM on Programming LanguagesJun 8More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMsNVIDIA · arXiv (Cornell University)Jun 7More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMsNVIDIA · arXiv (Cornell University)Jun 7The Minimal Retroreflective Microfacet ModelNVIDIA · arXiv (Cornell University)Jun 7Generalization in Nonlinear Least Squares via Learned Feature GeometryGoogle DeepMind · arXiv (Cornell University)Jun 7Parallel SMT Solving via Dynamic Partitioning, Core-Guided Pruning, and Backbone DetectionMicrosoft · arXiv (Cornell University)Jun 7Algebra of Bivariate-Bicycle Surface CodesAlphabet · arXiv (Cornell University)Jun 7From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over MemoryZhipu AI · arXiv (Cornell University)Jun 7Human-AI co-design for clinical prediction modelsMicrosoft · npj Digital Medicine2 citationsJun 6Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text GenerationAllen Institute for AI · arXiv (Cornell University)Jun 6Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine TranslationPreferred Networks · arXiv (Cornell University)Jun 6Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text GenerationAllen Institute for AI · arXiv (Cornell University)Jun 6Differentially Private Synthetic Data via APIs 4: Tabular DataMicrosoft · arXiv (Cornell University)Jun 6Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM AgentsAlibaba · arXiv (Cornell University)Jun 6Minibatch Selection for Language Models via Partition Matroid Constrained Gradient MatchingMicrosoft · arXiv (Cornell University)Jun 6GIScholarBench: Benchmarking LLM Overconfidence in GIS ResearchAlphabet · arXiv (Cornell University)Jun 6Exploring a novel data- and parameter-efficient fine-tuning method for robust face recognitioniFlytek · Pattern RecognitionJun 6Triangle Criterion: A Mixed-State Magic Criterion with Applications in Distillation and DetectionTechnology Innovation Institute · PRX Quantum2 citationsJun 5