Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
TimeCap: A Scalable Open-Source Pipeline for Captioning Wearable Health Time-Series DataAlphabet · arXiv (Cornell University)Oct 15SHIP: Structured and Hierarchical Insight with PrivacyAlphabet · arXiv (Cornell University)Oct 15Product Costing in Data PipelinesAlibaba · arXiv (Cornell University)Oct 15Data Strategies for Large Language Models: A Unified Perspective on the Training LifecycleMicrosoft · arXiv (Cornell University)Oct 15Stitched surface codes: planar concatenation through GHZ corridorsAlphabet · arXiv (Cornell University)Oct 15AgentEval: Evidence-Bounded Assessment of Stateful AgentsAlibaba · arXiv (Cornell University)Oct 15CIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for ClusteringAlibaba · arXiv (Cornell University)Oct 15Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language ModelsAlibaba · arXiv (Cornell University)Oct 15ReFlow: Replay-Driven Decoupling for Efficient RL Post-TrainingAlibaba · arXiv (Cornell University)Oct 15Bias Control and Injection for Multi-Agent AggregationMicrosoft · arXiv (Cornell University)Oct 15Towards Continual Learning: Mitigating Forgetting With Subspace TuningAlphabet · arXiv (Cornell University)Oct 15Does On-Policy Distillation Need to Complete Every Rollout?Alibaba · arXiv (Cornell University)Oct 15FDE-Gym: The Last Mile of AI DeliveryMicrosoft · arXiv (Cornell University)Oct 15MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment ScalingAlibaba · arXiv (Cornell University)Oct 15P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document ParsingAlibaba · arXiv (Cornell University)Oct 15Diviner: Agentic RCA with Human-Governed Adaptation for Large-Scale InfrastructureMeta · arXiv (Cornell University)Oct 15Recursive Reward Improvement via Adversarial Meta-Prompt EvolutionMicrosoft · arXiv (Cornell University)Oct 15Learning to Steer LLM Agents and Multi-Agent SystemsAlibaba · arXiv (Cornell University)Oct 15JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMsAlphabet · arXiv (Cornell University)Oct 153DCodeVerse: Exploring 3D Worlds as CodeGoogle DeepMind · arXiv (Cornell University)Oct 15A General Framework for Matching with DelaysAlphabet · arXiv (Cornell University)Oct 15Dendritic computation bridges neuroscience and foundation modelsAlibaba, MiniMax · Nature CommunicationsOct 15Magic state cultivation on a superconducting quantum processorAlphabet · ScienceOct 15EvolvingBrain: An Adaptive Skill System for Multi-modal Agents Self-Evolution in Open WorldsiFlytek · arXiv (Cornell University)Oct 14Zero-Shot Spoken Language Understanding with SLAM-ASR: What Do Monolingual ASR-Trained Linear Projectors Enable?Cohere · arXiv (Cornell University)Oct 14