Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Total-Editing: Head Avatar with Editable Appearance, Motion, and LightingMicrosoft · IEEE International Conference on Computer Vision Workshops2 citationsOct 19, 2025DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video UnderstandingAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)2 citationsOct 19, 2025Exploiting Policy Idling for Dexterous ManipulationGoogle DeepMind · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)2 citationsOct 19, 2025EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric PerceptionMeta · IEEE/CVF International Conference on Computer Vision (ICCV)2 citationsOct 19, 2025AlignDiff: Learning Physically-Grounded Camera Alignment via DiffusionAlphabet, Google DeepMind · IEEE/CVF International Conference on Computer Vision (ICCV)2 citationsOct 19, 2025Human-in-the-Loop Local Corrections of 3D Scene Layouts via InfillingMeta · IEEE/CVF International Conference on Computer Vision (ICCV)2 citationsOct 19, 2025Inter: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance SamplingAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)2 citationsOct 19, 2025Rethinking DPO-Style Diffusion Aligning FrameworksMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025DiffRefine: Diffusion-Based Proposal Specific Point Cloud Densification for Cross-Domain Object DetectionMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025Bridging Local Inductive Bias and Long-Range Dependencies With Pixel-Mamba for End-To-End Whole Slide Image AnalysisAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025A Linear N-Point Solver for Structure and Motion from Asynchronous TracksAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025Dirichlet-Constrained Variational Codebook Learning for Temporally Coherent Video Face RestorationAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025Hierarchical 3D Scene Graphs Construction OutdoorsAlphabet · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion PriorsAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025Overcoming Dual Drift for Continual Long-Tailed Visual Question AnsweringAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025MoMaps: Semantics-Aware Scene Motion Generation with Motion MapsAlphabet, Google DeepMind · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025GeoMan: Temporally Consistent Human Geometry Estimation Using Image-to-Video DiffusionNVIDIA · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025Genμ: The Generative Machine Unlearning ChallengeMeta · IEEE International Conference on Computer Vision Workshops1 citationOct 19, 2025TrafficVILA: Scaling Vision-Language Models to High-Resolution Video Understanding for Traffic Safety AnalysisNVIDIA · IEEE International Conference on Computer Vision Workshops1 citationOct 19, 2025Geometric Inductive Priors in Diffusion-Based Optical Flow EstimationMicrosoft · IEEE International Conference on Computer Vision Workshops1 citationOct 19, 2025Controllable and Expressive One-Shot Video Head SwappingAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025Bitrate-Controlled Diffusion for Disentangling Motion and Content in VideoMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)1 citationOct 19, 2025GeoFlow-SLAM: A Robust Tightly-Coupled RGBD-Inertial and Legged Odometry Fusion SLAM for Dynamic Legged RoboticsHorizon Robotics · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)1 citationOct 19, 2025ACGD: Visual Multitask Policy Learning with Asymmetric Critic Guided DistillationNVIDIA · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)1 citationOct 19, 2025UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial AttacksTechnology Innovation Institute · arXiv (Cornell University)1 citationOct 19, 2025