Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
RewardBench 2: Advancing Reward Model EvaluationAllen Institute for AI · arXiv (Cornell University)161 citationsJun 2, 2025Simulating Subjects: The Promise and Peril of Artificial Intelligence Stand-Ins for Social Agents and InteractionsAlphabet · Sociological Methods & Research48 citationsJun 2, 2025Esoteric Language Models: A Family of Any-Order Diffusion LLMsNVIDIA · arXiv (Cornell University)39 citationsJun 2, 2025Playing with Transformer at 30+ FPS via Next-Frame DiffusionMicrosoft · arXiv (Cornell University)18 citationsJun 2, 2025Quartic Quantum Speedups for Planted InferenceAlphabet · Physical Review X18 citationsJun 2, 2025Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MASMicrosoft · arXiv (Cornell University)13 citationsJun 2, 2025E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation ModelsNVIDIA · arXiv (Cornell University)9 citationsJun 2, 2025Automating Prompt Leakage Attacks on Large Language Models Using Agentic ApproachGoogle DeepMind · International Convention on Information and Communication Technology, Electronics and Microelectronics8 citationsJun 2, 2025GPU Accelerated High Capacity, AI-Ready 5G/6G Reference Design and Verification MethodologyNVIDIA · IEEE Wireless Communications3 citationsJun 2, 2025Detection and mapping of Antarctic lichen using drones, multispectral cameras, and supervised deep learningNVIDIA · International Journal of Applied Earth Observation and Geoinformation3 citationsJun 2, 2025Learning Abstract World Models with a Group-Structured Latent SpaceMicrosoft · arXiv (Cornell University)2 citationsJun 2, 2025Minimal Impact ControlNet: Advancing Multi-ControlNet IntegrationAlibaba · arXiv (Cornell University)1 citationJun 2, 2025Descriptive History Representations: Learning Representations by Answering QuestionsAlphabet, Google DeepMind · arXiv (Cornell University)Jun 2, 2025R2SM: Referring and Reasoning for Selective MasksNVIDIA · arXiv (Cornell University)Jun 2, 2025MotionBench: Benchmarking and Improving Fine-Grained Video Motion Understanding for Vision Language ModelsZhipu AI · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings51 citationsJun 1, 2025SuperRL: Reinforcement Learning with Supervision to Boost Language Model ReasoningMicrosoft · arXiv (Cornell University)23 citationsJun 1, 2025Dynamic Range-Filtering Approximate Nearest Neighbor SearchAlibaba · Proceedings of the VLDB Endowment16 citationsJun 1, 2025A review on synergizing knowledge graphs and large language modelsZhipu AI · Computing15 citationsJun 1, 2025From lab to fab: A large language model for chemical engineeringiFlytek · CHINESE JOURNAL OF CATALYSIS (CHINESE VERSION)14 citationsJun 1, 2025Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language ModelsAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings13 citationsJun 1, 2025SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMsNVIDIA · arXiv (Cornell University)12 citationsJun 1, 2025Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene UnderstandingMicrosoft · Computational Visual Media8 citationsJun 1, 2025Text2SQL Business Intelligence System Based on Retrieval‐Augmented Generation ( RAG )iFlytek · Engineering Reports3 citationsJun 1, 2025Bound by semanticity: universal laws governing the generalization-identification tradeoffMicrosoft · arXiv (Cornell University)2 citationsJun 1, 2025Sectric: Towards Accurate, Privacy-Preserving and Efficient Triangle CountingAlibaba · Proceedings of the VLDB Endowment2 citationsJun 1, 2025