Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Exponential Speed-ups for Structured Goemans-Williamson relaxations via Quantum Gibbs States and Pauli SparsityTechnology Innovation Institute · arXiv (Cornell University)1 citationOct 9, 2025LiveThinking: Enabling Real-Time Efficient Reasoning for AI-Powered Livestreaming via Reinforcement LearningAlibaba · arXiv (Cornell University)1 citationOct 9, 2025Optimal Stopping in Latent Diffusion ModelsGoogle DeepMind · arXiv (Cornell University)1 citationOct 9, 2025Generating Representative Macrobenchmark Microservice Systems from Distributed Traces with PaletteMicrosoft · ACM SIGOPS Asia-Pacific Workshop on Systems (APSys)1 citationOct 9, 2025ML-native Dataplane Operating SystemsMicrosoft · ACM SIGOPS Asia-Pacific Workshop on Systems (APSys)1 citationOct 9, 2025Gradual MetaprogrammingMeta · ACM SIGPLAN International Workshop on Type-Driven Development (TyDe)1 citationOct 9, 2025HieraSynth: A Parallel Framework for Complete Super-Optimization with Hierarchical Space DecompositionAlphabet · Proceedings of the ACM on Programming Languages1 citationOct 9, 2025BPL: Bias-Adaptive Preference Distillation Learning For Recommender SystemMicrosoft · IEEE Transactions on Knowledge and Data EngineeringOct 9, 2025Faster margin maximization rates for generic and adversarially robust optimization methodsAlphabet · Mathematical ProgrammingOct 9, 2025Poisoning Attacks on LLMs Require a Near-constant Number of Poison SamplesAnthropic · arXiv (Cornell University)142 citationsOct 8, 2025Flipping the Dialogue: Training and Evaluating User Language ModelsMicrosoft · arXiv (Cornell University)45 citationsOct 8, 2025NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM AgentsNVIDIA · arXiv (Cornell University)30 citationsOct 8, 2025The Markovian Thinker: Architecture-Agnostic Linear Scaling of ReasoningMicrosoft · arXiv (Cornell University)22 citationsOct 8, 2025h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement LearningMicrosoft · arXiv (Cornell University)9 citationsOct 8, 2025Position: Towards Responsible Evaluation for Text-to-SpeechMicrosoft · arXiv (Cornell University)6 citationsOct 8, 2025DevOps-Enabled Cloud-Native Architectures for Scalable and Resilient IoT Applications: A Kubernetes-Based ApproachMicrosoft · International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)3 citationsOct 8, 2025Revisiting put-that-there, context aware window interactions via LLMsAlphabet · IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)2 citationsOct 8, 2025The Honest Virtual Self? Effects of Avatar Personalization and Motor Control on Physiological Responses to Deceptive BehavioursMicrosoft · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR1 citationOct 8, 2025Attention-VR: predicting VIMS from attention-weighted multi-modal movement dataMeta · IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)Oct 8, 2025Meaningful Pose-Based Sign Language EvaluationGoogle DeepMind · arXiv (Cornell University)Oct 8, 2025xrWORKS’25: The 2nd International Workshop on Extended Reality for Knowledge WorkAlphabet · IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)Oct 8, 2025OMCR: An Online Multivariate Forecaster for Cloud Resource ManagementAlibaba · IEEE Transactions on Knowledge and Data EngineeringOct 8, 2025Secure DevOps with AI-Enhanced MonitoringMeta · International Journal of Computer Technology and Electronics CommunicationOct 8, 2025NorMuon: Making Muon more efficient and scalableMicrosoft · arXiv (Cornell University)82 citationsOct 7, 2025Taxonomy of User Needs and ActionsAlphabet · arXiv (Cornell University)21 citationsOct 7, 2025