Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Reflex: Visually Grounded Reactive Humanoid ControlAllen Institute for AI · arXiv (Cornell University)Oct 8Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE AgentsMicrosoft · arXiv (Cornell University)Oct 8Higher-Order Action Supervision Makes A Strong Policy ClassHorizon Robotics · arXiv (Cornell University)Oct 8SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent TracesAlibaba · arXiv (Cornell University)Oct 8Autonomous Code Migration for Quantum Programming Languages: A Case Study with QED-C BenchmarksNVIDIA · arXiv (Cornell University)Oct 8REMORY: Learning Residual Memory for Context CompactionAlibaba · arXiv (Cornell University)Oct 8Quickly extracting fidelity decay rates in random circuit benchmarking experimentsTechnology Innovation Institute · arXiv (Cornell University)Oct 8Beyond Sequences: Distilling Structured Decision Memory for LLM RecommendationAlibaba · arXiv (Cornell University)Oct 8UniData: Universal Multimodal Instruction Generation PipelineAlibaba · arXiv (Cornell University)Oct 8DPPM: Dual-Path Parametric Memory for Personalized Language ModelsiFlytek · arXiv (Cornell University)Oct 8When KL Regularization Misfires in Group Policy OptimizationAlibaba · arXiv (Cornell University)Oct 8V-CoLA: Vision Token Compression with Linear AttentionAlibaba · arXiv (Cornell University)Oct 8HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database EnvironmentsMicrosoft · arXiv (Cornell University)Oct 8EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program EvolutionSakana AI · arXiv (Cornell University)Oct 8From Prompting to Composing: A Spatial Canvas Interface for Poster GenerationMicrosoft · arXiv (Cornell University)Oct 8Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational AgentsAlibaba · arXiv (Cornell University)Oct 8When Interfaces Speak: Data-Aware Generative UI Harness for Active InteractionMicrosoft · arXiv (Cornell University)Oct 8When Should Agents Think? Adaptive Reasoning via Cross-Turn EstimationAlibaba · arXiv (Cornell University)Oct 8Latent Core Tokenizer: Compress, but MeaningfullyMicrosoft · arXiv (Cornell University)Oct 8SepGen: Multi-Stem Audio-Video Separation and Generation in a Single ModelAlphabet · arXiv (Cornell University)Oct 8Magic Pen: Automatic Pen Mode Switching for Document AnnotationMicrosoft · arXiv (Cornell University)Oct 8Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code RepairAlibaba · arXivOct 8Retrofitting language models to operate over bytesAllen Institute for AI · Nature2 citationsOct 7Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering AgentsMicrosoft · IEEE/ACM International Conference on Automated Software Engineering (ASE)2 citationsOct 7Regression Accumulation in Multi-turn LLM Programming ConversationsAlibaba · IEEE/ACM International Conference on Automated Software Engineering (ASE)1 citationOct 7