Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
A Unified 3D Object Perception Framework for Real-Time Outside-In Multi-Camera SystemsNVIDIA · arXiv (Cornell University)Jan 15Convex analysis for composite functions without K-convexityAlphabet · arXiv (Cornell University)Jan 15Scattering Processes from Quantum Simulation Algorithms for Scalar Field TheoriesAlphabet · PRX Quantum7 citationsJan 14Harnessing phytoconstituents to treat COVID-19 triggered acute respiratory distress syndrome: Insights from network pharmacology, and molecular modelingTechnology Innovation Institute · Phytochemistry Letters6 citationsJan 14On Your Own: Pro-Level Autonomous Drone Racing in Uninstrumented ArenasTechnology Innovation Institute · IEEE Robotics and Automation Letters5 citationsJan 14Research Code Sharing in Support of Gold Standard ScienceAlphabet · Journal of Diabetes Science and Technology4 citationsJan 14Distribution-Aligned Sequence Distillation for Superior Long-CoT ReasoningAlibaba · arXiv (Cornell University)2 citationsJan 14On Excess Risk Convergence Rates of Neural Network ClassifiersMicrosoft · IEEE Transactions on Information Theory2 citationsJan 14Improved Algorithms for Fair Matroid Submodular MaximizationMicrosoft · arXiv (Cornell University)Jan 14LatencyPrism: Online Non-intrusive Latency Sculpting for SLO-Guaranteed LLM InferenceAlibaba · arXiv (Cornell University)Jan 14Materializing Inter-Channel Relationships With Multi-Density Woodcock TrackingNVIDIA · IEEE Transactions on Visualization and Computer GraphicsJan 14Multiplex Thinking: Reasoning via Token-wise Branch-and-MergeMicrosoft · arXiv (Cornell University)1 citationJan 133AM: 3egment Anything with Adaptive Geometric Consistency in VideosNVIDIA · arXiv (Cornell University)1 citationJan 13Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMsAlibaba · arXiv (Cornell University)Jan 13Controlled LLM Training on Spectral SphereMicrosoft · arXiv (Cornell University)Jan 13User-Oriented Multi-Turn Dialogue Generation with Tool Use at scaleUpstage · arXiv (Cornell University)Jan 13AugMMRev: An LLM-Augmented Multimodal Ranking Model for Personalized Image Material RetrievalAlibaba · IEEE Transactions on Consumer Electronics10 citationsJan 12Lost in the Noise: How Reasoning Models Fail with Contextual DistractorsLG AI Research · arXiv (Cornell University)4 citationsJan 12Real-time error mitigation for variational optimization on quantum hardwareTechnology Innovation Institute · Physical Review Research4 citationsJan 12Reward Modeling from Natural Language Human FeedbackAlibaba · arXiv (Cornell University)2 citationsJan 12Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA EvaluationLG AI Research · arXiv (Cornell University)2 citationsJan 12Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical CognitionMeta · arXiv (Cornell University)1 citationJan 12Rewarding Creativity: A Human-Aligned Generative Reward Model for Reinforcement Learning in StorytellingAlibaba · arXiv (Cornell University)1 citationJan 12MegaFlow: Large-Scale Distributed Orchestration System for the Agentic EraAlibaba · arXiv (Cornell University)1 citationJan 12Safety Evaluation of Motion Plans Using Trajectory Predictors as Forward Reachable Set EstimatorsNVIDIA · IEEE Robotics and Automation Letters1 citationJan 12