Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical SegmentationAlibaba · arXiv (Cornell University)Oct 3Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure ExperienceNVIDIA · arXiv (Cornell University)Oct 3Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End LatencyMeta · arXiv (Cornell University)Oct 3From Probe Scores to Alarm Policies: Operational Validity of Activation Monitors for Language-Model AgentsAlibaba · arXiv (Cornell University)Oct 3The GPU Resilience Lottery: Understanding and Taming Real-World Hardware Errors in Heterogeneous AI InfrastructureAlibaba · ACM Transactions on Architecture and Code OptimizationOct 3Generalization Bounds for Flow-matching Generative Models for Intrinsically Low-dimensional DataGoogle DeepMind · arXiv (Cornell University)Oct 2HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing AgentsAlibaba · arXiv (Cornell University)Oct 2High-Rate Quantum Codes with Proven Distance and Low-Weight MeasurementsTechnology Innovation Institute · arXiv (Cornell University)Oct 2MLCommons Jailbreak Benchmark v1.0Google DeepMind · arXiv (Cornell University)Oct 2Optimal Convergence of Iterative Methods for DatalogoMicrosoft · arXiv (Cornell University)Oct 2Training Numerical Intelligence via Auto-Diagnosis and Skill DiscoveryAlibaba · arXiv (Cornell University)Oct 2CUAWright: A Minimal Unified Interface for Digital AgentsMicrosoft · arXiv (Cornell University)Oct 2DUET: Co-Evolving Solver and Grader AgentsMicrosoft · arXiv (Cornell University)Oct 2Dynamic Expert Pruning for Multi-Agent SystemsMicrosoft · arXiv (Cornell University)Oct 2Query Performance Tuning with Optimal Exploration of Optimizer Cost Model Parameter SpaceMicrosoft · arXiv (Cornell University)Oct 2Generalization Bounds for Flow-matching Generative Models for Intrinsically Low-dimensional DataGoogle DeepMind · arXiv (Cornell University)Oct 2D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?Alibaba · arXiv (Cornell University)Oct 2Root-sparsity scaling for Hamiltonian simulation, differential equations and linear-system solversAlphabet · arXiv (Cornell University)Oct 2Single-Shot Error Correction at Optimal Spacetime CostTechnology Innovation Institute · arXiv (Cornell University)Oct 2RaBitQ-SSD: Split Codes and Pipelined I/O for SSD-Resident Vector SearchMeta · arXiv (Cornell University)Oct 2Rubric-Based Optimization for Text-to-Music GenerationAllen Institute for AI · arXiv (Cornell University)Oct 2Learning to Revise Reasoning with Segment-wise On-Policy DistillationAlibaba · arXiv (Cornell University)Oct 2CorrectGuard: Eyes-Off Correctness Estimation for Black-Box Security GuardrailsMicrosoft · arXiv (Cornell University)Oct 2Jumping up and down: Denoiser diffusion models for discrete ordinal dataSakana AI · arXiv (Cornell University)Oct 2Understanding Enrichment in Reinforcement LearningMicrosoft · arXiv (Cornell University)Oct 2