Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion ModelsAlphabet · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)100 citationsJun 11, 2025Splat-SLAM: Globally Optimized RGB-Only SLAM with 3D GaussiansAlphabet · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)98 citationsJun 11, 2025IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased DecodingAlibaba · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)96 citationsJun 11, 2025Generative AI for Film Creation: A Survey of Recent AdvancesAlphabet · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)56 citationsJun 11, 2025An Interactive Agent Foundation ModelMicrosoft · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)49 citationsJun 11, 2025Securing the Skies: a Comprehensive Survey on Anti-Uav Methods, Benchmarking, and Future DirectionsMicrosoft · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)48 citationsJun 11, 2025Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal ModelsMicrosoft · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)48 citationsJun 11, 2025Prompt Categories Cluster for Weakly Supervised Semantic SegmentationMicrosoft · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)34 citationsJun 11, 2025How Good is my Video-LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMsAlphabet · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)28 citationsJun 11, 2025NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and ResultsMicrosoft · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)26 citationsJun 11, 2025LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-TuningSenseTime · arXiv (Cornell University)24 citationsJun 11, 2025NTIRE 2025 Challenge on UGC Video Enhancement: Methods and ResultsAlibaba · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)21 citationsJun 11, 2025CoRT: Code-integrated Reasoning within ThinkingAlibaba · arXiv (Cornell University)18 citationsJun 11, 2025Event-Based Eye Tracking. 2025 Event-Based Vision WorkshopNVIDIA · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)15 citationsJun 11, 2025Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language ModelsAlibaba · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)10 citationsJun 11, 2025Self-Predictive Representations for Combinatorial Generalization in Behavioral CloningGoogle DeepMind · arXiv (Cornell University)9 citationsJun 11, 2025On the Robustness of GUI Grounding Models Against Image AttacksMicrosoft · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)8 citationsJun 11, 2025Understanding Depth and Height Perception in Large Visual-Language ModelsMicrosoft · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)8 citationsJun 11, 2025DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech RepresentationsAlibaba · arXiv (Cornell University)7 citationsJun 11, 2025A Large-Scale Analysis on Contextual Self-Supervised Video Representation LearningMicrosoft · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)6 citationsJun 11, 2025Scaling On-Device GPU Inference for Large Generative ModelsAlphabet, Meta · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)5 citationsJun 11, 2025Visually Interpretable Subtask Reasoning for Visual Question AnsweringNVIDIA · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)4 citationsJun 11, 2025Training Neural Networks on RAW and HDR Images for Restoration TasksMeta · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)3 citationsJun 11, 2025On the Suitability of Reinforcement Fine-Tuning to Visual TasksSenseTime · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)3 citationsJun 11, 2025Full Stack Video Conferencing App using TypeScript and NextJSMicrosoft · International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS)3 citationsJun 11, 2025