Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Scaling On-Device GPU Inference for Large Generative ModelsAlphabet, Meta · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)5 citationsJun 11, 2025Exemplar Masking for Multimodal Incremental LearningAlphabet · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)2 citationsJun 11, 2025How Good is my Video-LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMsAlphabet · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)1 citationJun 11, 2025Throughput Measurements and Profile Analysis of Cloud NetworksAlphabet · IEEE Transactions on Networking1 citationJun 11, 2025D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object RecognitionAlphabet · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)Jun 11, 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/Proceedings37 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/Proceedings32 citationsJun 10, 2025A Bias-Free Training Paradigm for More General AI-generated Image DetectionGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings28 citationsJun 10, 2025ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-TuningAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings18 citationsJun 10, 2025VLOGGER: Multimodal Diffusion for Embodied Avatar SynthesisGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings16 citationsJun 10, 2025Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated ContentAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings15 citationsJun 10, 20253D-GSW: 3D Gaussian Splatting for Robust WatermarkingGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings14 citationsJun 10, 2025Scaling Inference Time Compute for Diffusion ModelsAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings14 citationsJun 10, 2025Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric VideosAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings13 citationsJun 10, 2025Stereo4D: Learning How Things Move in 3D from Internet Stereo VideosGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings12 citationsJun 10, 2025Zero-Shot Styled Text Image Generation, but Make It AutoregressiveAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings12 citationsJun 10, 2025Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual RecognitionAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings12 citationsJun 10, 2025Flexible Frame Selection for Efficient Video ReasoningGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings11 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/Proceedings11 citationsJun 10, 2025Perception Tokens Enhance Visual Reasoning in Multimodal Language ModelsAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings11 citationsJun 10, 2025The Power of Context: How Multimodality Improves Image Super-ResolutionAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings9 citationsJun 10, 2025Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein DistortionGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings8 citationsJun 10, 2025Gaussian Eigen Models for Human HeadsAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings8 citationsJun 10, 2025LogiCzsl: Exploring Logic-induced Representation for Compositional Zero-shot LearningAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings8 citationsJun 10, 2025MP-SfM: Monocular Surface Priors for Robust Structure-From-MotionAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings7 citationsJun 10, 2025