Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Accelerating Speculative Diffusions via Block VerificationAlphabet · arXiv (Cornell University)Jun 11Fully Distributed Multi-View 3D Tracking in Real-TimeNVIDIA · arXiv (Cornell University)Jun 11MiniMax Sparse AttentionNVIDIA · arXiv (Cornell University)Jun 11SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI AssistantsAlibaba · arXiv (Cornell University)Jun 11ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement LearningAlibaba · arXiv (Cornell University)Jun 11EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific DiscoveryZhipu AI · arXiv (Cornell University)Jun 11Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial ReasoningNVIDIA · arXiv (Cornell University)Jun 11Operadic consistency: a label-free signal for compositional reasoning failures in LLMsAllen Institute for AI · arXiv (Cornell University)Jun 11Conditional Execution of Transpiler Passes Based on Per-Script Feature DetectionAlphabet · State Of the Art in Java Program AnalysisJun 11DeduBB: Binary Code Size Reduction via Post-Link Basic Block DeduplicationAlphabet · ACM SIGPLAN/SIGBED Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES)Jun 11Scaling Static Code Analysis Adoption at WhatsApp iOSMeta · State Of the Art in Java Program AnalysisJun 11Improved quantum processor logical error rates via correction and detectionMicrosoft · Nature3 citationsJun 10Explainability Under Risk: A Decision-Centric Framework for Critical AI SystemsNVIDIA · International Conference on Inventive Computing and Informatics (ICICI)Jun 10A Comprehensive Ecosystem for Open-Domain Customized Video GenerationMicrosoft · arXiv (Cornell University)Jun 10Findings of the MAGMaR 2026 Shared TaskOpenAI · arXiv (Cornell University)Jun 10GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal ModelsMicrosoft · arXiv (Cornell University)Jun 10PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt InjectionsAlphabet · arXiv (Cornell University)Jun 10APPO: Agentic Procedural Policy OptimizationAlibaba · arXiv (Cornell University)Jun 10VIPIR: A Versatile GPU Framework for Integrating Private Information Retrieval ProtocolsNVIDIA · arXiv (Cornell University)Jun 10A Comprehensive Ecosystem for Open-Domain Customized Video GenerationMicrosoft · arXiv (Cornell University)Jun 10Context-Driven Incremental Compression for Multi-Turn Dialogue GenerationNVIDIA · arXiv (Cornell University)Jun 10Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMsAllen Institute for AI · arXiv (Cornell University)Jun 10Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning GeneralizationAlibaba · arXiv (Cornell University)Jun 10RLCSD: Reinforcement Learning with Contrastive On-Policy Self-DistillationAlibaba · arXiv (Cornell University)Jun 10Findings of the MAGMaR 2026 Shared TaskOpenAI · arXiv (Cornell University)Jun 10