Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Optimization of Rank Losses for Image RetrievalGoogle DeepMind · IEEE Transactions on Pattern Analysis and Machine Intelligence6 citationsFeb 20, 2025Toward Sustainable and Secure Smart Internet of Buildings Using Advanced Communication SystemsTechnology Innovation Institute · IEEE Network5 citationsFeb 20, 2025Inversed Pyramid Network with Spatial-adapted and Task-oriented Tuning for few-shot learningSenseTime · Pattern Recognition5 citationsFeb 20, 2025PREM: Privately Answering Statistical Queries with Relative ErrorAlphabet · arXiv (Cornell University)4 citationsFeb 20, 2025Joint Luminance-Chrominance Learning for Image DebandingAlibaba · IEEE Transactions on Circuits and Systems for Video Technology3 citationsFeb 20, 2025CrossOver: 3D Scene Cross-Modal AlignmentMicrosoft · arXiv (Cornell University)1 citationFeb 20, 2025Make-A-Character 2: Animatable 3D Character Generation From a Single ImageAlibaba · Qeios1 citationFeb 20, 2025Multi-Agent Risks from Advanced AIGoogle DeepMind · arXiv (Cornell University)303 citationsFeb 19, 2025Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code GenerationNVIDIA · ACM Transactions on Design Automation of Electronic Systems91 citationsFeb 19, 2025Autellix: An Efficient Serving Engine for LLM Agents as General ProgramsGoogle DeepMind · arXiv (Cornell University)84 citationsFeb 19, 2025ActionPiece: Contextually Tokenizing Action Sequences for Generative RecommendationGoogle DeepMind · arXiv (Cornell University)49 citationsFeb 19, 2025World and Human Action Models towards gameplay ideationMicrosoft · Nature36 citationsFeb 19, 2025In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor SearchMicrosoft · arXiv (Cornell University)32 citationsFeb 19, 2025Judging the Judges: A Collection of LLM-Generated Relevance JudgementsMicrosoft · arXiv (Cornell University)25 citationsFeb 19, 2025RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache CompressionNVIDIA · arXiv (Cornell University)19 citationsFeb 19, 2025Breaking the mold: Overcoming the time constraints of molecular dynamics on general-purpose hardwareCerebras Systems · The Journal of Chemical Physics13 citationsFeb 19, 2025Proving Olympiad Inequalities by Synergizing LLMs and Symbolic ReasoningMicrosoft · arXiv (Cornell University)12 citationsFeb 19, 2025LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference OptimizationAlibaba · arXiv (Cornell University)11 citationsFeb 19, 2025Preliminary Study on Fine-Grained Power and Energy Measurements on Grace Hopper GH200 with Open-Source Performance ToolsNVIDIA · International Conference on High Performance Computing in Asia-Pacific Region Workshops (HPC Asia Workshops)4 citationsFeb 19, 2025PCIe Bandwidth-Aware Scheduling for Multi-Instance GPUsNVIDIA · International Conference on High Performance Computing in Asia-Pacific Region (HPC Asia)4 citationsFeb 19, 2025THE EVOLUTION OF GPU INFRASTRUCTURE: BEST PRACTICES FOR ENTERPRISE AI DEPLOYMENTSMeta · INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND INFORMATION TECHNOLOGYFeb 19, 2025Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language ModelsAlibaba · arXiv (Cornell University)Feb 19, 2025Program Merge: What's Deep Learning Got to Do with It?Meta, Microsoft · Communications of the ACMFeb 19, 2025Prevalence and Prevention of Large Language Model Use in Crowd WorkMicrosoft · Communications of the ACM73 citationsFeb 18, 2025REALTALK: A 21-Day Real-World Dataset for Long-Term ConversationDatabricks · arXiv (Cornell University)38 citationsFeb 18, 2025