Research

A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.

Field
Lab

13,663 papers in Computer Science, newest first. Some proceedings carry OpenAlex's date of January 1.

Timestep Embedding Tells: It’s Time to Cache for Video Diffusion ModelAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings139 citationsJun 10, 2025Design Patterns for Securing LLM Agents against Prompt InjectionsMicrosoft · arXiv (Cornell University)132 citationsJun 10, 2025Gen3C: 3D-Informed World-Consistent Video Generation with Precise Camera ControlNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings128 citationsJun 10, 2025Magma: A Foundation Model for Multimodal AI AgentsMicrosoft · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings121 citationsJun 10, 2025VISTA3D: A Unified Segmentation Foundation Model For 3D Medical ImagingNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings120 citationsJun 10, 2025JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and GenerationDeepSeek · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings118 citationsJun 10, 2025CAT4D: Create Anything in 4D with Multi-View Video Diffusion ModelsGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings116 citationsJun 10, 2025MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic VideosGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings110 citationsJun 10, 2025Towards Practical Real-Time Neural Video CompressionMicrosoft · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings107 citationsJun 10, 2025Motion Prompting: Controlling Video Generation with Motion TrajectoriesGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings105 citationsJun 10, 20255%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition TasksAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings104 citationsJun 10, 2025Tora: Trajectory-oriented Diffusion Transformer for Video GenerationAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings102 citationsJun 10, 2025Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference OptimizationMicrosoft · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings96 citationsJun 10, 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion ModelsNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings87 citationsJun 10, 2025Improving Diffusion Inverse Problem Solving with Decoupled Noise AnnealingNVIDIA, OpenAI · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings84 citationsJun 10, 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/Proceedings83 citationsJun 10, 2025DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion ModelsNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings82 citationsJun 10, 2025MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 SecondsMeta · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings82 citationsJun 10, 2025LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language ModelsAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings80 citationsJun 10, 2025RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for RoboticsNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings79 citationsJun 10, 2025StableAnimator: High-Quality Identity-Preserving Human Image AnimationMicrosoft · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings76 citationsJun 10, 2025HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View VideosMeta · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings73 citationsJun 10, 2025LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language ModelsAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings66 citationsJun 10, 2025MIMO: Controllable Character Video Synthesis with Spatial Decomposed ModelingAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings65 citationsJun 10, 2025Simpler Diffusion: 1.5 FID on ImageNet512 with pixel-space diffusionAlphabet, Google DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings65 citationsJun 10, 2025