Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Pushback in a Haystack: Language Models Respond to Factual Errors Ambiguously and IneffectivelyAllen Institute for AI · arXiv (Cornell University)Oct 13APT: Feedback-Driven Agentic Post-Training for Text-to-Image GenerationMicrosoft · arXiv (Cornell University)Oct 13Failure Recovery via Belief Updates and World Modeling for Long-Horizon AgentsAlphabet · arXiv (Cornell University)Oct 13A Better-than-2 Approximation for k-Median Part I: The Power of General BidsAlphabet · arXiv (Cornell University)Oct 13ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?Alibaba · arXiv (Cornell University)Oct 13ScenePercept: Scenario-Conditioned Perceptual Assessment of Real-World User-Generated Content ImagesAlibaba · arXiv (Cornell University)Oct 13Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent SkillsAlibaba · arXiv (Cornell University)Oct 13Input-Conditioned Search for Efficient Test-Time Scaling of Recursive ReasonersMicrosoft · arXiv (Cornell University)Oct 13PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test RewardsAlphabet · arXiv (Cornell University)Oct 13Multimodal Contrastive Representation Learning Based Voice Conversion for Electrolaryngeal Speech EnhancementAlibaba · arXiv (Cornell University)Oct 13RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement LearningAlibaba · arXiv (Cornell University)Oct 13Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal MemoryAlibaba · arXiv (Cornell University)Oct 13No Truly Sublogarithmic-Round Algorithm for Distributed MIS in the LOCAL ModelAlphabet · arXiv (Cornell University)Oct 13Graph Metanetworks for Transformer Based Language ModelsNVIDIA · arXiv (Cornell University)Oct 13$T$-efficient unitary synthesis via block-sparse Hamiltonian simulationMicrosoft · arXiv (Cornell University)Oct 13Cowork-Gym: Synthesizing Interactive Work Environments at ScaleAlibaba · arXiv (Cornell University)Oct 13The Federated Tumor Segmentation and Classification (FeTS++) ChallengeNVIDIA · arXiv (Cornell University)Oct 13LoOPSD: On-Policy Self-Distillation with Looped TeachersAlibaba · arXiv (Cornell University)Oct 13LatentRemedy: Efficient Remedy For Non-Prefix KV Cache Reuse in Multi-Agent SystemsMicrosoft · arXiv (Cornell University)Oct 13GLST: Global-Local Spatio-Temporal Memory Decomposition Framework for Online Chained-Goal NavigationNVIDIA · arXiv (Cornell University)Oct 13PPVM: A Circuit Simulation Framework for Digital Twins of Quantum ProcessorsNVIDIA · arXiv (Cornell University)Oct 13LongForcing: Scaling Temporal Manifold Matching for Long-Horizon World RolloutAlibaba · arXiv (Cornell University)Oct 13Two For The Price Of One: Curvature-Aware Pruning Preserves Influence Functions TooAlphabet · arXiv (Cornell University)Oct 13World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World ModelsMicrosoft · arXiv (Cornell University)Oct 12Compositional RL: Evaluating and Training LLMs for Collaborative ReasoningNVIDIA · arXiv (Cornell University)Oct 12