Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video GenerationSenseTime · arXiv (Cornell University)11 citationsOct 9, 2025Optimal and Robust In-situ Quantum Hamiltonian Learning through ParallelizationAlphabet · arXiv (Cornell University)8 citationsOct 9, 2025Hardness of recognizing phases of matterAlphabet · arXiv (Cornell University)8 citationsOct 9, 2025Robust Heuristic Algorithm Design with LLMsMicrosoft · arXiv (Cornell University)7 citationsOct 9, 2025ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive EvaluationMicrosoft · arXiv (Cornell University)5 citationsOct 9, 2025Random unitaries that conserve energyAlphabet · arXiv (Cornell University)5 citationsOct 9, 2025Translation Validation for LLVM’s AArch64 BackendNVIDIA · Proceedings of the ACM on Programming Languages5 citationsOct 9, 2025The Continuous Tensor Abstraction: Where Indices Are RealNVIDIA · Proceedings of the ACM on Programming Languages5 citationsOct 9, 2025Transmuting prompts into weightsAlphabet · arXiv (Cornell University)4 citationsOct 9, 2025A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement LearningAlibaba · arXiv (Cornell University)4 citationsOct 9, 2025GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language ModelsSenseTime · arXiv (Cornell University)4 citationsOct 9, 2025Mind the Abstraction Gap: Bringing Equality Saturation to Real-World ML CompilersOpenAI · Proceedings of the ACM on Programming Languages4 citationsOct 9, 2025Memory-Safety Verification of Open Programs with Angelic AssumptionsMicrosoft · Proceedings of the ACM on Programming Languages4 citationsOct 9, 2025SafeRace: Assessing and Addressing WebGPU Memory Safety in the Presence of Data RacesMicrosoft · Proceedings of the ACM on Programming Languages4 citationsOct 9, 2025Work Packets: A New Abstraction for GC Software Engineering, Optimization, and InnovationAlphabet · Proceedings of the ACM on Programming Languages4 citationsOct 9, 2025Computationally-efficient Graph Modeling with Refined Graph Random FeaturesAlphabet, Google DeepMind · arXiv (Cornell University)3 citationsOct 9, 2025Who Said Neural Networks Aren't Linear?NVIDIA · arXiv (Cornell University)3 citationsOct 9, 2025Learning T-conjugated stabilizers: The multiple-squares dihedral StateHSPAlphabet · arXiv (Cornell University)3 citationsOct 9, 2025Towards Fully Disaggregated Recommendation Model ServingMeta · ACM SIGOPS Asia-Pacific Workshop on Systems (APSys)3 citationsOct 9, 2025DCITNet: A Temporal Forecasting Scheme for IT Power Demand of Data CenterAlibaba · IEEE Transactions on Industry Applications3 citationsOct 9, 2025Indispensable CPU-centric Checkpointing for GPUsMicrosoft · ACM SIGOPS Asia-Pacific Workshop on Systems (APSys)2 citationsOct 9, 2025Advancing Performance via a Systematic Application of Research and Industrial Best PracticeAlphabet · Proceedings of the ACM on Programming Languages2 citationsOct 9, 2025Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-ExpertsMicrosoft · arXiv (Cornell University)1 citationOct 9, 2025Towards Human-Like Grading: A Unified LLM-Enhanced Framework for Subjective Question EvaluationAlibaba · arXiv (Cornell University)1 citationOct 9, 2025VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-BiddingAlibaba · arXiv (Cornell University)1 citationOct 9, 2025