Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal UnderstandingSenseTime · IEEE Transactions on Pattern Analysis and Machine Intelligence3 citationsJul 28, 2025A survey of low-bit large language models: Basics, systems, and algorithmsSenseTime · Neural Networks16 citationsJul 15, 2025VisionTraj: A Noise-Robust Trajectory Recovery Framework Based on Large-Scale Camera NetworkSenseTime · IEEE Transactions on Intelligent Transportation Systems1 citationJul 9, 2025Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion ModelsSenseTime · IEEE International Conference on Multimedia and Expo (ICME)Jun 30, 2025Topology-Aware Virtualization over Inter-Core Connected Neural Processing UnitsSenseTime · Proceedings - International Symposium on Computer Architecture/Proceedings3 citationsJun 20, 2025On the Suitability of Reinforcement Fine-Tuning to Visual TasksSenseTime · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)3 citationsJun 11, 2025OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?SenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings21 citationsJun 10, 2025Docopilot: Improving Multimodal Models for Document-Level UnderstandingSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings13 citationsJun 10, 2025MatAnyone: Stable Video Matting with Consistent Memory PropagationSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings11 citationsJun 10, 2025F-LMM: Grounding Frozen Large Multimodal ModelsSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings10 citationsJun 10, 2025TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage FusionSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings10 citationsJun 10, 2025Universal Actions for Enhanced Embodied Foundation ModelsSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings9 citationsJun 10, 2025StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene GenerationSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings7 citationsJun 10, 2025PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language ModelsSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings6 citationsJun 10, 2025Shining Yourself: High-Fidelity Ornaments Virtual Try-on with Diffusion ModelSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token FoldingSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025Unsupervised Continual Domain Shift Learning with Multi-Prototype ModelingSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025SpiritSight Agent: Advanced GUI Agent with One LookSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings3 citationsJun 10, 2025SFDM: Robust Decomposition of Geometry and Reflectance for Realistic Face Rendering from Sparse-view ImagesSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings1 citationJun 10, 2025NADER: Neural Architecture Design via Multi-Agent CollaborationSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings1 citationJun 10, 2025See Further When Clear: Curriculum Consistency ModelSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings1 citationJun 10, 2025HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language EmbeddingSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings1 citationJun 10, 2025DriveScape: High-Resolution Driving Video Generation by Multi-View Feature FusionSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/ProceedingsJun 10, 2025Zero6DOT: Zero-Shot 6D Object Pose Tracking With Monocular RGB VideoSenseTime · IEEE Transactions on Circuits and Systems for Video Technology3 citationsJun 9, 2025OpenUni: A Simple Baseline for Unified Multimodal Understanding and GenerationSenseTime · arXiv (Cornell University)May 29, 2025