Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
The 9th AI City ChallengeNVIDIA · IEEE International Conference on Computer Vision Workshops21 citationsOct 19, 2025Boosting MLLM Reasoning with Text-Debiased Hint-GRPOAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)21 citationsOct 19, 2025VPO: Aligning Text-to-Video Generation Models with Prompt OptimizationZhipu AI · IEEE/CVF International Conference on Computer Vision (ICCV)21 citationsOct 19, 2025SemTalk: Holistic Co-Speech Motion Generation with Frame-Level Semantic EmphasisAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)21 citationsOct 19, 2025FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale FusionAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)21 citationsOct 19, 2025MedSegFactory: Text-Guided Generation of Medical Image-Mask PairsNVIDIA · IEEE/CVF International Conference on Computer Vision (ICCV)20 citationsOct 19, 2025Vision-Language Models Can't See the ObviousTechnology Innovation Institute · IEEE/CVF International Conference on Computer Vision (ICCV)20 citationsOct 19, 2025PUMA: Empowering Unified MLLM with Multi-Granular Visual GenerationSenseTime · IEEE/CVF International Conference on Computer Vision (ICCV)20 citationsOct 19, 2025ICE-Bench: A Unified and Comprehensive Benchmark for Image Creating and EditingAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)19 citationsOct 19, 2025DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent SpaceNVIDIA · IEEE/CVF International Conference on Computer Vision (ICCV)19 citationsOct 19, 2025SignRep: Enhancing Self-Supervised Sign RepresentationsMeta · IEEE/CVF International Conference on Computer Vision (ICCV)19 citationsOct 19, 2025USP: Unified Self-Supervised Pretraining for Image Generation and UnderstandingAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)19 citationsOct 19, 2025Orchid: Image Latent Diffusion for Joint Appearance and Geometry GenerationGoogle DeepMind · IEEE/CVF International Conference on Computer Vision (ICCV)19 citationsOct 19, 2025PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic DegradationAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)19 citationsOct 19, 2025Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control is Easier than You ThinkAlibaba · IEEE International Conference on Computer Vision Workshops18 citationsOct 19, 2025SITE: Towards Spatial Intelligence Thorough EvaluationMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)18 citationsOct 19, 2025Synthetica: Large Scale Synthetic Data Generation for Robot PerceptionNVIDIA · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)17 citationsOct 19, 2025YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement LearningNVIDIA · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)17 citationsOct 19, 2025Perception-as-Control: Fine-Grained Controllable Image Animation with 3D-Aware Motion RepresentationAlibaba · IEEE/CVF International Conference on Computer Vision (ICCV)17 citationsOct 19, 2025Controllable 3D Outdoor Scene Generation via Scene GraphsNVIDIA · IEEE/CVF International Conference on Computer Vision (ICCV)16 citationsOct 19, 2025Gaussian Variation Field Diffusion for High-Fidelity Video-to-4D SynthesisMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)16 citationsOct 19, 2025AV-Flow: Transforming Text to Audio-Visual Human-Like InteractionsMeta · IEEE/CVF International Conference on Computer Vision (ICCV)16 citationsOct 19, 2025RoMo: Robust Motion Segmentation Improves Structure from MotionGoogle DeepMind · IEEE/CVF International Conference on Computer Vision (ICCV)16 citationsOct 19, 2025REDUCIO! Generating 1K Video Within 16 Seconds Using Extremely Compressed Motion LatentsMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)15 citationsOct 19, 2025StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image StreamsMicrosoft · IEEE/CVF International Conference on Computer Vision (ICCV)14 citationsOct 19, 2025