Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
MYA-EWS: A Real-Time Anomalous Event Warning Framework Fusing Target Detection and Semantic ReasoningMeta · International Conference on Signal Processing Systems (ICSPS)Oct 24, 2025TURBOTEST: Learning When Less is Enough through Early Termination of Internet Speed TestsAlphabet · arXiv (Cornell University)Oct 24, 2025ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test CasesAnthropic · arXiv (Cornell University)51 citationsOct 23, 2025DeepWideSearch: Benchmarking Depth and Width in Agentic Information SeekingAlibaba · arXiv (Cornell University)27 citationsOct 23, 2025CreativityPrism: A Cross-Domain Evaluation Framework for Large Language Model CreativityAllen Institute for AI · arXiv (Cornell University)22 citationsOct 23, 2025UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-ReasoningAlibaba · arXiv (Cornell University)20 citationsOct 23, 2025ULMGNN: Fragmented layer grouping in GUI designs through graph learning based on multimodal informationAlibaba · Neurocomputing1 citationOct 23, 2025AdaDoS: Adaptive DoS Attack via Deep Adversarial Reinforcement Learning in SDNAlibaba · arXiv (Cornell University)Oct 23, 2025Source-Resilient Joint Learning Framework for Preserving Stable Generalization on Diverse Ultrasonic Source ScenariosNVIDIA · IEEE Journal of Biomedical and Health InformaticsOct 23, 2025Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific DataAlibaba · IEEE Transactions on Big DataOct 23, 2025Self-distilled learning of adaptive interval 3D lookup tables on real-time image enhancementAlibaba · Pattern RecognitionOct 23, 2025Optimization by decoded quantum interferometryAlphabet · Nature100 citationsOct 22, 2025olmOCR 2: Unit Test Rewards for Document OCRAllen Institute for AI · arXiv (Cornell University)56 citationsOct 22, 2025Discovering state-of-the-art reinforcement learning algorithmsGoogle DeepMind · Nature35 citationsOct 22, 2025BugPilot: Complex Bug Generation for Efficient Learning of SWE SkillsMicrosoft · arXiv (Cornell University)32 citationsOct 22, 2025Quantum computation of molecular geometry via many-body nuclear spin echoesAlphabet, Google DeepMind · arXiv (Cornell University)26 citationsOct 22, 2025LoongRL: Reinforcement Learning for Advanced Reasoning over Long ContextsMicrosoft · arXiv (Cornell University)19 citationsOct 22, 2025RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMsAlphabet · arXiv (Cornell University)16 citationsOct 22, 2025SNRAware: Improved Deep Learning MRI Denoising with Signal-to-Noise Ratio Unit Training and G-Factor Map AugmentationMicrosoft · Radiology Artificial Intelligence9 citationsOct 22, 2025Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and BeyondMicrosoft · arXiv (Cornell University)8 citationsOct 22, 2025SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large SpreadsheetsMicrosoft · arXiv (Cornell University)8 citationsOct 22, 2025Facilitating Trust in AI-assisted Software ToolsMicrosoft · ACM Transactions on Software Engineering and Methodology8 citationsOct 22, 2025HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule ApplicationAlibaba · arXiv (Cornell University)5 citationsOct 22, 2025TheMCPCompany: Creating General-purpose Agents with Task-specific ToolsMicrosoft · arXiv (Cornell University)5 citationsOct 22, 2025The Art of Asking: Multilingual Prompt Optimization for Synthetic DataCohere · arXiv (Cornell University)4 citationsOct 22, 2025