Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
GPU-Accelerated Simulations of Moving Boundary Problems and Fluid-Structure Interaction at Extreme ScalesNVIDIA · AIAA AVIATION ForumJun 4Bankrupting DoS attackersMeta · Theoretical Computer Science2 citationsJun 3Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agentsMicrosoft · arXiv (Cornell University)1 citationJun 3Octopus: An ABR-RAN Closed-Loop Approach Towards High QoE Multi-User 5G VR GamingAlibaba · IEEE International Conference on Sensing, Communication, and Networking (SECON)Jun 3SocraticPO: Policy Optimization via Interactive GuidanceiFlytek · arXiv (Cornell University)Jun 3Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agentsMicrosoft · arXiv (Cornell University)Jun 3Search-Time Contamination in Deep Research Agents: Measuring Performance Inflation in Public Benchmark EvaluationAlibaba · arXiv (Cornell University)Jun 3X4Val: Learning Neural Surrogates for Variance-Reduced Policy EvaluationNVIDIA · arXiv (Cornell University)Jun 3Scaling Self-Evolving Agents via Parametric MemoryAlibaba · arXiv (Cornell University)Jun 3Ultra-Fast Neural Video CompressionMicrosoft · arXiv (Cornell University)Jun 3Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language ModelsMicrosoft · arXiv (Cornell University)Jun 3DSIRM: Learning Query-Bridged Discrete Semantic Identifiers for E-commerce Relevance ModelingAlibaba · arXiv (Cornell University)Jun 3BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical RoutineAlibaba · arXiv (Cornell University)Jun 3AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement LearningAlibaba · arXiv (Cornell University)Jun 3Context-as-AI-Service: Surfacing Cross-File Dependency Chains for LLM-Generated Developer DocumentationMeta · arXiv (Cornell University)Jun 3Google’s Training Supercomputers From TPUv2 to Ironwood: Architectural Stability, Scale, Resilience, Power Efficiency, and Sustainability Across Five GenerationsAlphabet · IEEE MicroJun 3Quantum-error-correction-inspired multiparameter quantum metrologyAlphabet · Physical Review AJun 3SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and PracticeMicrosoft · arXiv (Cornell University)Jun 2POLARIS: Guiding Small Models to Write Long StoriesAlphabet · arXiv (Cornell University)Jun 2EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise KnowledgeAlibaba · arXiv (Cornell University)Jun 2EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement LearningAlibaba · arXiv (Cornell University)Jun 2ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search AgentsAlibaba · arXiv (Cornell University)Jun 2When Model Merging Breaks Routing: Training-Free Calibration for MoEMeta · arXiv (Cornell University)Jun 2NVIDIA Isaac Sim: Enabling Scalable, GPU-Accelerated Simulation for RoboticsNVIDIA · arXiv (Cornell University)Jun 2Beyond "To whom it may concern": Tailoring Machine Translation to Audience and IntentAlphabet · arXiv (Cornell University)Jun 2