Computer VisionLast updated on May 24, 2026From machine perception to spatial intelligence, with a side of computational photography.Computer Vision Reasoning Deep Learning Adversarial RobustnessPublicationsMining Attribute Subspaces for Efficient Fine-tuning of 3D Foundation ModelsWith the emergence of 3D foundation models, there is growing interest in fine-tuning them for downstream tasks, where LoRA is the …Yu Jiang, Hanwen Jiang, Ahmed Abdelkader, Wen-Sheng Chu, Brandon Y. Feng, Zhangyang Wang, Qixing HuangCite Project arXivMull-Tokens: Modality-Agnostic Latent ThinkingReasoning goes beyond language; the real world requires reasoning about space, time, affordances, and much more that words alone cannot …Arijit Ray, Ahmed Abdelkader, Chengzhi Mao, Bryan A. Plummer, Kate Saenko, Ranjay Krishna, Leonidas Guibas, Wen-Sheng ChuCite Project Webpage arXiv CodeMarginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth EstimatesStructure-from-Motion (SfM) is a fundamental 3D vision task for recovering camera parameters and scene geometry from multi-view images. …Shengjie Zhu, Ahmed Abdelkader, Mark J. Matthews, Xiaoming Liu, Wen-Sheng ChuCite Project Webpage OpenReview arXiv Code
