Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
RL-RC-DoT: A Block-level RL agent for Task-Aware Video CompressionNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025Frequency-Biased Synergistic Design for Image Compression and CompensationAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025I2VGuard: Safeguarding Images against Misuse in Diffusion-based Image-to-Video ModelsMicrosoft · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025A Physics-Informed Blur Learning Framework for Imaging SystemsNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025Synthetic Visual GenomeAllen Institute for AI · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image GenerationMeta · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance ModelingAlphabet · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025Associative TransformerMicrosoft · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings5 citationsJun 10, 2025Dynamic Region Ownership for Concurrency SafetyMicrosoft · Proceedings of the ACM on Programming Languages5 citationsJun 10, 2025Uncertainty Prioritized Experience ReplayGoogle DeepMind · arXiv (Cornell University)4 citationsJun 10, 2025Learnable Spatial-Temporal Positional Encoding for Link PredictionMeta · arXiv (Cornell University)4 citationsJun 10, 2025Volumetric Surfaces: Representing Fuzzy Geometries with Layered MeshesMeta · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMsGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Zero-Shot 4D Lidar Panoptic SegmentationNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025See Further When Clear: Curriculum Consistency ModelSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Enhancing Adversarial Transferability with Checkpoints of a Single Model’s TrainingMicrosoft · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image CompressionAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Scaling Vision Pre-Training to 4K ResolutionNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image GenerationAlphabet, Google DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-ThoughtNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Motions as Queries: One-Stage Multi-Person Holistic Human Motion CaptureAlibaba · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Context-Aware Multimodal PretrainingGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Random Conditioning with Distillation for Data-Efficient Diffusion Model CompressionNVIDIA · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025Visual Lexicon: Rich Image Features in Language SpaceGoogle DeepMind · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language EmbeddingSenseTime · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings4 citationsJun 10, 2025