Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Stabilizing Reinforcement Learning with LLMs: Formulation and PracticesAlibaba · arXiv (Cornell University)55 citationsDec 1, 2025SAGESERVE: Optimizing LLM Serving on Cloud Data Centers with Forecast Aware Auto-ScalingMicrosoft · Proceedings of the ACM on Measurement and Analysis of Computing Systems41 citationsDec 1, 2025Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block ScalingNVIDIA · arXiv (Cornell University)40 citationsDec 1, 2025The Art of Scaling Test-Time Compute for Large Language ModelsMicrosoft · arXiv (Cornell University)21 citationsDec 1, 2025NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation PredictionAlibaba · arXiv (Cornell University)18 citationsDec 1, 2025LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through ChessGoogle DeepMind · arXiv (Cornell University)17 citationsDec 1, 2025Dion2: A Simple Method to Shrink Matrix in MuonMicrosoft · arXiv (Cornell University)14 citationsDec 1, 2025ReXVQA: A Large-scale Visual Question Answering Benchmark for Generalist Chest X-ray UnderstandingSakana AI · Pacific Symposium on Biocomputing (PSB)14 citationsDec 1, 2025ViT$^3$: Unlocking Test-Time Training in VisionAlibaba · arXiv (Cornell University)14 citationsDec 1, 2025CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RLAlibaba · arXiv (Cornell University)12 citationsDec 1, 2025MeshAgent: Enabling Reliable Network Management with Large Language ModelsMicrosoft · Proceedings of the ACM on Measurement and Analysis of Computing Systems12 citationsDec 1, 2025Unified architecture for quantum lookup tablesMicrosoft · Physical Review Research11 citationsDec 1, 2025AI-Native 6G: Empowering Intelligent RAN With Accelerated ComputeNVIDIA · IEEE Wireless Communications9 citationsDec 1, 2025Discrete differential geometry for simulating nonlinear behaviors of flexible systems: A surveyHorizon Robotics · Extreme Mechanics Letters8 citationsDec 1, 2025TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table RecognitionSenseTime · arXiv (Cornell University)7 citationsDec 1, 2025Harmonic Caching for Walk on SpheresNVIDIA · ACM Transactions on Graphics6 citationsDec 1, 2025Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMsAlibaba · arXiv (Cornell University)6 citationsDec 1, 2025Sparse Matrix Factorization for Scalable Machine Learning in Cloud EnvironmentsMicrosoft · International Conference on NexGen Networks and Cybernetics (IC2NC)5 citationsDec 1, 2025Probabilistic Reasoning in Multi-Agent Reinforcement Learning SystemsMicrosoft · International Conference on NexGen Networks and Cybernetics (IC2NC)5 citationsDec 1, 2025Practical Gaussian Process Implicit Surfaces with Sparse ConvolutionsNVIDIA · ACM Transactions on Graphics5 citationsDec 1, 2025RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving PoliciesNVIDIA · arXiv (Cornell University)5 citationsDec 1, 2025Efficient Reconstruction, Benchmarking and Validation of Cross-Talk Models in Readout Noise in Near-Term Quantum DevicesTechnology Innovation Institute · Open Systems & Information Dynamics4 citationsDec 1, 2025Robust Derivative Estimation with Walk on StarsNVIDIA · ACM Transactions on Graphics4 citationsDec 1, 2025Realistic Cloth Rendering with a Ray-Wave Hybrid Shading ModelNVIDIA · ACM Transactions on Graphics3 citationsDec 1, 2025Generalized Unbiased Reconstruction for Gradient-Domain RenderingNVIDIA · ACM Transactions on Graphics3 citationsDec 1, 2025