Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
CC-OCR V2: Fine-Grained Attribution of LMM Failures in Real-World Visual Document UnderstandingAlibaba · arXiv (Cornell University)May 5Agentic-imodels: Evolving agentic interpretability tools via autoresearchMicrosoft · arXiv (Cornell University)May 5EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative RubricsAllen Institute for AI · arXiv (Cornell University)May 5Anonymous Credentials from ECDSAAlphabet · IACR Communications in Cryptology3 citationsMay 4Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?Microsoft · arXiv (Cornell University)May 4Learning Correct Behavior from Examples: Validating Sequential Execution in Autonomous AgentsMicrosoft · arXiv (Cornell University)May 4On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon LengthMicrosoft · arXiv (Cornell University)May 4Generalized Distributional Alignment Games for Unbiased Answer-Level Fine-TuningAlphabet · arXiv (Cornell University)May 4Soft-to-Hard Routing in Sparse Mixture-of-Experts ModelsMeta · arXiv (Cornell University)May 4More Efficient Lattice-based OLEMeta · IACR Communications in CryptologyMay 4Quantum Error Correction Faces Another HurdleTechnology Innovation Institute · PhysicsMay 4Active multiple matrix completion with adaptive confidence setsGoogle DeepMind · arXiv (Cornell University)May 4FixItFlow: Automated Troubleshooting Guide Generation from Cloud IncidentsMicrosoft · arXiv (Cornell University)May 3DexSim2Real: Foundation Model-Guided Sim-to-Real Transfer for Generalizable Dexterous ManipulationAlibaba · arXiv (Cornell University)May 3Benchmarking quantum trial wavefunctions for phaseless auxiliary-field quantum Monte CarloNVIDIA · arXiv (Cornell University)May 3Only Say What You Know: Calibration-Aware Generation for Long-Form FactualityMicrosoft · arXiv (Cornell University)May 3Cross-Layer Energy Analysis of Multimodal Training on Grace Hopper SuperchipsMicrosoft · arXiv (Cornell University)May 3VIDA: A Dataset for Visually Dependent Ambiguity in Multimodal Machine TranslationAlibaba · arXiv (Cornell University)May 3Improving protein-ligand complex generation with force field guidanceNVIDIA · Journal of Cheminformatics1 citationMay 2Regularized Centered Emphatic Temporal Difference LearningMicrosoft · arXiv (Cornell University)May 2GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language ModelsAlibaba · arXiv (Cornell University)May 2OmniEncoder: See, Hear, and Feel Continuous Motion Like Humans With One EncoderAlibaba · arXiv (Cornell University)May 2GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language ModelsAlibaba · arXiv (Cornell University)May 2MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent DebateAlibaba · arXiv (Cornell University)May 2Hallucinations Undermine Trust; Metacognition is a Way ForwardAlphabet · arXiv (Cornell University)May 2