Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
DiT4SR: Taming Diffusion Transformer for Real-World Image Super-ResolutionSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)18 citationsOct 19, 2025Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action PolicySenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)10 citationsOct 19, 2025ViLLa: Video Reasoning Segmentation with Large Language ModelSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)8 citationsOct 19, 2025DPoser-X: Diffusion Model as Robust 3D Whole-Body Human Pose PriorNVIDIA, SenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)7 citationsOct 19, 2025Harmonizing Visual Representations for Unified Multimodal Understanding and GenerationSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)5 citationsOct 19, 2025Event-Guided HDR Reconstruction with Diffusion PriorsSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)4 citationsOct 19, 2025Spatial Preference Rewarding for MLLMs Spatial UnderstandingSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)4 citationsOct 19, 2025SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style TransferSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)4 citationsOct 19, 2025UniMLVG: Unified Framework for Multi-View Long Video Generation with Comprehensive Control Capabilities for Autonomous DrivingSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)3 citationsOct 19, 2025TokensGen: Harnessing Condensed Tokens for Long Video GenerationSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)2 citationsOct 19, 2025PUMA: Empowering Unified MLLM with Multi-Granular Visual GenerationSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)2 citationsOct 19, 2025Monochromatic Event Guided Image Deblurring with Event-Triggering-Aware DecompositionSenseTime · IEEE International Conference on Computer Vision WorkshopsOct 19, 2025From Gallery to Wrist: Realistic 3D Bracelet Insertion in VideosSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)Oct 19, 2025Pretrained Reversible Generation as Unsupervised Visual Representation LearningSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)Oct 19, 2025LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video GenerationSenseTime · arXiv (Cornell University)Oct 9, 2025GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language ModelsSenseTime · arXiv (Cornell University)Oct 9, 2025Characterizing Mobile SoC for Accelerating Heterogeneous LLM InferenceSenseTime · ACM SIGOPS Symposium on Operating Systems Principles (SOSP)13 citationsOct 1, 2025OctoPipe: Reducing Pipeline Bubbles for Heterogeneous Models via Co-Optimizing Partitioning, Placement, and SchedulingSenseTime · arXiv (Cornell University)Sep 28, 2025Multimodal mathematical reasoning embedded in aerial vehicle imagery: Benchmarking, analysis, and explorationSenseTime · ISPRS Journal of Photogrammetry and Remote Sensing3 citationsSep 24, 2025Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM EraSenseTime · International Joint Conference on Artificial Intelligence11 citationsSep 1, 2025MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced PolicySenseTime · arXiv (Cornell University)Aug 7, 2025MM-instruct: Generated visual instructions for large multimodal model alignmentSenseTime · Neurocomputing1 citationAug 5, 2025Enhancing HDR Imaging with Joint Denoising and DeblurringSenseTime · International Journal of Computer Vision2 citationsAug 4, 2025Blockchain-powered secure trading framework for power dispatch in metaverseSenseTime · IET conference proceedings.Aug 1, 2025LCA ‐ NeRF : Large‐Scale Scene Neural Rendering With Clustered Appearance EmbeddingSenseTime · Transactions in GISAug 1, 2025