Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Relatos de ex-alunos e colaboradores sobre suas experiências no LaMuTMeta · Revista Brasileira de MúsicaJan 31Bounds for Hardness Condensation in the Query ModelMicrosoft · arXiv (Cornell University)Jan 31Supervised sparse auto-encoders for interpretable and compositional representationsHugging Face · arXiv (Cornell University)Jan 31How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool UseMicrosoft · arXiv (Cornell University)Jan 31PaperBanana: Automating Academic Illustration for AI ScientistsAlphabet · arXiv (Cornell University)6 citationsJan 30RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World RepositoriesAlibaba · arXiv (Cornell University)3 citationsJan 30Deterministic Multi-Agent Incident Assistance: Separating Routing from Tool Execution to Improve Reliability in Production AIOpsMicrosoft · International Journal of Engineering Science and Information TechnologyJan 30AI-Driven Personalization across Domains for Local Categorical Query Understanding and Context-Aware RetrievalAlphabet · International Conference on Artificial Intelligence, Digital Media Technology and Social Computing (ICAIDS)Jan 30Unveiling the Potential of Quantization with MXFP4: Strategies for Quantization Error ReductionMeta · arXiv (Cornell University)Jan 30DIVERGE: Diversity-Enhanced RAG for Open-Ended Information SeekingMicrosoft · arXiv (Cornell University)Jan 30EUGens: Efficient, Unified, and General Dense LayersAlphabet, Google DeepMind · arXiv (Cornell University)Jan 30Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVRAlibaba · arXiv (Cornell University)Jan 30Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language ModelsMeta · arXiv (Cornell University)Jan 30Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective PredictionMeta · arXiv (Cornell University)Jan 30Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality AssessmentAlibaba · arXiv (Cornell University)Jan 30UPA: Unsupervised Prompt Agent via Tree-Based Search and SelectionMininglamp Technology · arXiv (Cornell University)Jan 30From Abstract to Contextual: What LLMs Still Cannot Do in MathematicsMicrosoft · arXiv (Cornell University)Jan 30HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playingMiniMax · arXiv (Cornell University)4 citationsJan 29PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy OptimizationMicrosoft · arXiv (Cornell University)3 citationsJan 29Towards universal X-ray security inspection: a benchmark and stereoscopic-aware oriented prohibited item detection frameworkiFlytek, SenseTime · Science China Information Sciences1 citationJan 29Lost in Space? Vision-Language Models Struggle with Relative Camera Pose EstimationNVIDIA · arXiv (Cornell University)1 citationJan 29Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic ToolchainsAlibaba · arXiv (Cornell University)Jan 29LLM Compression by Block Removal with Constrained Binary OptimizationMultiverse Computing · arXiv (Cornell University)Jan 29ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning ModelsNVIDIA · arXiv (Cornell University)Jan 29DP-λCGD: Efficient Noise Correlation for Differentially Private Model TrainingAlphabet · arXiv (Cornell University)Jan 29