Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Fed-ADApt: Federated Anytime Depth Adaptation for Resource-Aware Medical Image SegmentationNVIDIA · arXiv (Cornell University)Oct 2Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashingMicrosoft · arXiv (Cornell University)Oct 2Beyond Entropy: Self-Diagnostic Multi-Role Token Optimization for Video ReasoningAlibaba · arXiv (Cornell University)Oct 2Fault-tolerant and fully addressable unitary logical gates via round-robin sparsificationAlphabet · arXiv (Cornell University)Oct 2ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open UniverseNVIDIA · arXiv (Cornell University)Oct 2The Recognition-Consequence Gap: How Gesture Recognition Misses Human ActionMicrosoft · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTIONOct 2Introduction to the Special Section on SOSP 2024Alphabet · ACM Transactions on Computer SystemsOct 2Quantifying 3D Pointing: Characterizing What Happens During Pointing Selection in Virtual RealityMeta · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTIONOct 2"Great! The Next Step Is...": In Pursuit of Proactive Assistance with Multimodal Foundation ModelsMicrosoft · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTIONOct 2Grounding AI Agents in Contracts: An Empirical Evaluation of Spec-Driven Test GenerationAlphabet · arXivOct 2Relight: Simple User-Level Checkpointing and Fast-Forward Replay for Distributed Task-Based SystemsNVIDIA · Proceedings of the ACM on Programming Languages1 citationOct 1Efficient Extraction for Effectful E-graphsAlphabet · Proceedings of the ACM on Programming Languages1 citationOct 1Equivalence Checking of ML GPU KernelsMicrosoft · Proceedings of the ACM on Programming Languages1 citationOct 1Denario Project: Deep Knowledge Artificial Intelligence Agents for Scientific DiscoveryGoogle DeepMind · PRX Intelligence1 citationOct 1MDeID: A dataset for multilingual medical de-identificationMicrosoft · Journal of Biomedical InformaticsOct 1Exponentially Compressed and Garbage-Free Alias Sampling for Polynomial State PreparationMicrosoft · arXiv (Cornell University)Oct 1An open vision-language model for diverse medical applicationsAlphabet · Nature MedicineOct 1Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart SpacesNVIDIA · arXiv (Cornell University)Oct 1Multivariate Quantum Signal ProcessingAlphabet · arXiv (Cornell University)Oct 1ActiveSaddler: Automated Curriculum Learning for Agent Harness OptimizationMicrosoft · arXiv (Cornell University)Oct 1Managing Context and Communication in Distributed Agentic UAV SwarmsTechnology Innovation Institute · arXiv (Cornell University)Oct 1MoLE: Mixture of Latent Experts for Complementary Visual ReasoningAlibaba · arXiv (Cornell University)Oct 1Efficient certification of time-reversal symmetry requires entanglementTechnology Innovation Institute · arXiv (Cornell University)Oct 1Function-like pseudorandom unitaries generate pseudorandom quantum processesTechnology Innovation Institute · arXiv (Cornell University)Oct 1DeFA: Dependency-Guided Failure Attribution for LLM AgentsAlibaba · arXiv (Cornell University)Oct 1