Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate SpaceAlphabet · arXiv (Cornell University)May 11Surviving Partial Rank Failures in Wide Expert-Parallel MoE InferenceAlibaba · arXiv (Cornell University)May 11Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching ModelsMicrosoft · arXiv (Cornell University)May 11Engineering Robustness into Personal Agents with the AI Workflow StoreAlphabet · arXiv (Cornell University)May 11Tensor Product Representation Probes Reveal Shared Structure Across Linear DirectionsAlphabet · arXiv (Cornell University)May 11Convex Optimization with Local Label Differential Privacy: Tight Bounds in All Privacy RegimesAlphabet · arXiv (Cornell University)May 11RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable RewardsAlphabet · arXiv (Cornell University)May 11EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied AgentsMicrosoft · arXiv (Cornell University)May 11STEPS: Selective On-Policy Self-Distillation for ReasoningAlibaba · arXiv (Cornell University)May 11How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken DialogueSenseTime · arXiv (Cornell University)May 11SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language NavigationAlphabet · arXiv (Cornell University)May 11DeepRefine: Agentic Knowledge Refinement via Reinforcement LearningMicrosoft · arXiv (Cornell University)May 11V-ABS: Action-Observer Driven Beam Search for Dynamic Visual ReasoningSenseTime · arXiv (Cornell University)May 11SCALAR: A Neurosymbolic Framework for Automated Conjecture and Reasoning in Quantum Circuit AnalysisNVIDIA · arXiv (Cornell University)May 11Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVRMicrosoft · arXiv (Cornell University)May 11MaD Physics: Evaluating information seeking under constraints in physical environmentsGoogle DeepMind · arXiv (Cornell University)May 11Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent MemoryMeta · arXiv (Cornell University)May 11LoKA: Low-precision Kernel Applications for Recommendation Models At ScaleMeta · arXiv (Cornell University)May 11An Interpretable Multi-Modal Ensemble Framework for Breast Cancer Analysis Using Imaging, Omics and Biomedical LiteratureMicrosoft · International Journal of Online and Biomedical Engineering (iJOE)May 11Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI AgentsMicrosoft · arXiv (Cornell University)May 10Online Steiner Forest with RecourseMicrosoft · arXiv (Cornell University)May 10Simpson's Paradox in Behavioral Curves: How Aggregation Distorts Parametric Models of User DynamicsMeta · arXiv (Cornell University)May 10Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI AgentsMicrosoft · arXiv (Cornell University)May 10Workspace Optimization: How to Train Your AgentNVIDIA · arXiv (Cornell University)May 10ML-CLIPSim: Multi-Layer CLIP Similarity for Machine-Oriented Image QualityAlphabet · arXiv (Cornell University)May 10