Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Teaching LLMs to Learn Tool Trialing and Execution through Environment InteractionAlibaba · arXiv (Cornell University)Jan 19A Benchmark for Language Models in Real-World System BuildingMicrosoft · arXiv (Cornell University)Jan 19Incentivizing In-depth Reasoning over Long Contexts with Process Advantage ShapingAlibaba · arXiv (Cornell University)1 citationJan 18Operational Intelligence for SAP: How AI Agents Transform Incident Response and System HealthMicrosoft · International Journal of Science Research and TechnologyJan 18A Unified Neural Codec Language Model for Selective Editable Text to Speech GenerationMicrosoft · arXiv (Cornell University)Jan 18Probabilistic modeling of disparity uncertainty for robust and efficient stereo matchingAlibaba · Pattern RecognitionJan 18Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line InterfacesAllen Institute for AI, Anthropic · arXiv (Cornell University)27 citationsJan 17Assessing LLM Reliability on Temporally Recent Open-Domain QuestionsAlphabet · arXiv (Cornell University)1 citationJan 17MuseAgent-1: Interactive Grounded Multimodal Understanding of Music Scores and Performance AudioMicrosoft · arXiv (Cornell University)Jan 17WW-FL: Secure and Private Large-Scale Federated LearningTechnology Innovation Institute · IACR Transactions on Cryptographic Hardware and Embedded Systems7 citationsJan 16Sota Voce: Low-Noise Sampling of Sparse Fixed-Weight VectorsTechnology Innovation Institute · IACR Transactions on Cryptographic Hardware and Embedded Systems2 citationsJan 16Anomaly Sample Detection for Deep Learning based Teaching Data CollectioniFlytek · International Conference on Informatics Education and Computer Technology Applications (IECA)Jan 16Do explanations generalize across large reasoning models?Microsoft · arXiv (Cornell University)Jan 16Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMsAlibaba · arXiv (Cornell University)Jan 16FORESTLLM: Large Language Models Make Random Forest Great on Few-shot Tabular LearningMicrosoft · arXiv (Cornell University)Jan 16Your One-Stop Solution for AI-Generated Video DetectionAlibaba · arXiv (Cornell University)Jan 16The Assistant Axis: Situating and Stabilizing the Default Persona of Language ModelsAnthropic · arXiv (Cornell University)23 citationsJan 15Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and GroundingAllen Institute for AI · arXiv (Cornell University)18 citationsJan 15Reasoning Models Generate Societies of ThoughtAlphabet · arXiv (Cornell University)9 citationsJan 15Practical Continual Forgetting for Pre-Trained Vision ModelsSenseTime · IEEE Transactions on Pattern Analysis and Machine Intelligence3 citationsJan 15DyDiT++: Diffusion Transformers With Timestep and Spatial Dynamics for Efficient Visual GenerationAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence3 citationsJan 15ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection AttackNVIDIA · arXiv (Cornell University)2 citationsJan 15The Spatial Blindspot of Vision-Language ModelsCohere · arXiv (Cornell University)2 citationsJan 15DecisionLLM: Large Language Models for Long Sequence Decision ExplorationAlibaba · arXiv (Cornell University)1 citationJan 15BYOL: Bring Your Own Language Into LLMsMicrosoft · arXiv (Cornell University)Jan 15