Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
MFCQA: Multi-Range Feature Cross-Attention Mechanism for no-reference image quality assessmentAlibaba · Knowledge-Based Systems7 citationsJan 17, 2025Textoon: Generating Vivid 2D Cartoon Characters from Text DescriptionsAlibaba · arXiv (Cornell University)6 citationsJan 17, 2025SCALING MACHINE LEARNING PIPELINES: A COMPREHENSIVE GUIDE TO LARGE-SCALE PERSONALIZATION SYSTEMSMeta · INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGYJan 17, 2025Omni-Emotion: Extending Video MLLM with Detailed Face and Audio Modeling for Multimodal Emotion AnalysisAlibaba · arXiv (Cornell University)47 citationsJan 16, 2025AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image GenerationAlibaba · arXiv (Cornell University)22 citationsJan 16, 2025Task Vectors in In-Context Learning: Emergence, Formation, and BenefitMicrosoft · arXiv (Cornell University)21 citationsJan 16, 2025YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality TasksAlphabet · arXiv (Cornell University)9 citationsJan 16, 2025AI-Enhanced Disaster Recovery Strategies for SAP S/4HANA in the CloudMicrosoft · International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI)3 citationsJan 16, 2025UVRM: A Scalable 3D Reconstruction Model from Unposed VideosMicrosoft · arXiv (Cornell University)1 citationJan 16, 2025Building Safer and Interoperable AI systemsAlphabet · Communications of the ACMJan 16, 2025OmniTracker: Unifying Visual Object Tracking by Tracking-With-DetectionMicrosoft · IEEE Transactions on Pattern Analysis and Machine Intelligence47 citationsJan 15, 2025Joint speech and text machine translation for up to 100 languagesMeta · Nature46 citationsJan 15, 2025Summon a demon and bind it: A grounded theory of LLM red teamingNVIDIA · PLoS ONE34 citationsJan 15, 2025Narrative Player: Reviving Data Narratives With VisualsMicrosoft · IEEE Transactions on Visualization and Computer Graphics25 citationsJan 15, 2025SPICED+: Syntactical Bug Pattern Identification and Correction of Trojans in A/MS Circuits Using LLM-Enhanced DetectionNVIDIA · IEEE Transactions on Very Large Scale Integration (VLSI) Systems18 citationsJan 15, 2025Octopus: Enhancing CXL Memory Pods via Sparse TopologyMicrosoft · arXiv (Cornell University)16 citationsJan 15, 2025LeMo: Enabling LEss Token Involvement for MOre Context Fine-tuningMicrosoft · arXiv (Cornell University)5 citationsJan 15, 2025HBSS: (Simple) hash-based stateless signatures – hash all the way to the rescue!Alphabet · Cryptography and Communications2 citationsJan 15, 2025Parameter-free dynamic fidelity selection for automated machine learningPreferred Networks · Applied Soft Computing2 citationsJan 15, 2025PhonemeVec: A Phoneme-Level Contextual Prosody Representation For Speech SynthesisiFlytek · ACM Transactions on Asian and Low-Resource Language Information Processing1 citationJan 15, 2025An efficient compaction scheme for LSM-based storage system via lightweight mergesZhipu AI · International Conference on Optoelectronic Information and Optical Engineering (OIOE)Jan 15, 2025Roadmap on Neuromorphic PhotonicsMicrosoft · arXiv (Cornell University)54 citationsJan 14, 2025A comprehensive review of network pruning based on pruning granularity and pruning time perspectivesAlibaba · Neurocomputing29 citationsJan 14, 2025Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question AnsweringAlibaba · arXiv (Cornell University)26 citationsJan 14, 2025Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement LearningMicrosoft · IEEE Transactions on Pattern Analysis and Machine Intelligence20 citationsJan 14, 2025