Computational Vision | UC Irvinehttps://vision.ics.uci.edu/publications/Recent publicationsBenchmarking Deep Learning for Future Liver Remnant Segmentation in Colorectal Liver Metastasishttps://vision.ics.uci.edu/papers/benchmarking-deep-learning-for-future-liver-remnant-segmentation-2026/https://vision.ics.uci.edu/papers/benchmarking-deep-learning-for-future-liver-remnant-segmentation-2026/Anthony T. Wu, Arghavan Rezvani, Kela Liu, Roozbeh Houshyar, Pooya Khosravi, Whitney Li, Xiaohui Xie. ISBI, 2026.Camera Control for Text-to-Image Generation via Learning Viewpoint Tokenshttps://vision.ics.uci.edu/papers/camera-control-for-text-to-image-generation-via-2026/https://vision.ics.uci.edu/papers/camera-control-for-text-to-image-generation-via-2026/Xinxuan Lu, Charless Fowlkes, Alexander C. Berg. CVPR, 2026.Compositional Reasoning via Joint Image and Language Decompositionhttps://vision.ics.uci.edu/papers/compositional-reasoning-via-joint-image-and-language-decomposition-2026/https://vision.ics.uci.edu/papers/compositional-reasoning-via-joint-image-and-language-decomposition-2026/Dwip Dalal, Madhav Kanda, Zhenhailong Wang, Heng Ji, Unnat Jain. EACL (Findings), 2026.Constructive Distortion: Improving MLLMs with Attention-Guided Image Warpinghttps://vision.ics.uci.edu/papers/constructive-distortion-improving-mllms-with-attention-guided-image-2025/https://vision.ics.uci.edu/papers/constructive-distortion-improving-mllms-with-attention-guided-image-2025/Dwip Dalal, Gautam Vashishtha, Utkarsh Mishra, Jeonghwan Kim, Madhav Kanda, Hyeonjeong Ha, Svetlana Lazebnik, Heng Ji, Unnat Jain. ICLR, 2026.CRAFT: A Tendon-Driven Hand with Hybrid Hard-Soft Compliancehttps://vision.ics.uci.edu/papers/craft-a-tendon-driven-hand-with-hybrid-hard-2026/https://vision.ics.uci.edu/papers/craft-a-tendon-driven-hand-with-hybrid-hard-2026/Leo Lin, Shivansh Patel, Jay Moon, Svetlana Lazebnik, Unnat Jain. CoRR, 2026.DeVA: Decoupled Video-Action Model with physical guidance for robot policy learninghttps://vision.ics.uci.edu/papers/deva-decoupled-video-action-model-with-physical-guidance-2026/https://vision.ics.uci.edu/papers/deva-decoupled-video-action-model-with-physical-guidance-2026/Mengqi Zhang, Sahil Khose, Simar Kareer, Yuchen Song, Unnat Jain, Judy Hoffman. CoRR, 2026.EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the Worldhttps://vision.ics.uci.edu/papers/egoverse-an-egocentric-human-dataset-for-robot-learning-2026/https://vision.ics.uci.edu/papers/egoverse-an-egocentric-human-dataset-for-robot-learning-2026/Ryan Punamiya, Simar Kareer, Zeyi Liu, Josh Citron, Ri-Zhao Qiu, Xiongyi Cai, Alexey Gavryushin, Jiaqi Chen, Davide Liconti, Lawrence Y. Zhu, Patcharapong Aphiwetsa, Baoyu Li, Aniketh Cheluva, Pranav Kuppili, Yangcen Liu, Dhruv Patel, Aidan Gao, Hye-Young Chung, Ryan Co, Renee Zbizika, Jeff Liu, Xiaomeng Xu, Haoyu Xiong, Geng Chen, Sebastiano Oliani, Chenyu Yang, Xi Wang, James Fort, Richard A. Newcombe, Josh Gao, Jason Chong, Garrett Matsuda, Aseem Doriwala, Marc Pollefeys, Robert K. Katzschmann, Xiaolong Wang, Shuran Song, Judy Hoffman, Danfei Xu. CoRR, 2026.Forecasting 3D Scanpaths in Egocentric Videohttps://vision.ics.uci.edu/papers/forecasting-3d-scanpaths-in-egocentric-video-2026/https://vision.ics.uci.edu/papers/forecasting-3d-scanpaths-in-egocentric-video-2026/Fiona Ryan, Ishwarya Ananthabhotla, Yijun Qian, Judy Hoffman, James M. Rehg, Vamsi Krishna Ithapu, Calvin Murdock. CVPR, 2026.Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignmenthttps://vision.ics.uci.edu/papers/generalizable-vla-finetuning-via-representation-anchoring-and-language-2026/https://vision.ics.uci.edu/papers/generalizable-vla-finetuning-via-representation-anchoring-and-language-2026/Dwip Dalal, Shivansh Patel, Chahit Jain, Jeonghwan Kim, Utkarsh Mishra, Alex Baratian, Hyeonjeong Ha, Heng Ji, Svetlana Lazebnik, Unnat Jain. CoRR, 2026.Posterior Augmented Flow Matchinghttps://vision.ics.uci.edu/papers/posterior-augmented-flow-matching-2026/https://vision.ics.uci.edu/papers/posterior-augmented-flow-matching-2026/George Stoica, Sayak Paul, Matthew Wallingford, Vivek Ramanujan, Abhay Nori, Winson Han, Ali Farhadi, Ranjay Krishna, Judy Hoffman. CoRR, 2026.Resolving Interference (RI): Disentangling Models for Improved Model Merginghttps://vision.ics.uci.edu/papers/resolving-interference-ri-disentangling-models-for-improved-model-2026/https://vision.ics.uci.edu/papers/resolving-interference-ri-disentangling-models-for-improved-model-2026/Pratik Ramesh, George Stoica, Arun Iyer, Leshem Choshen, Judy Hoffman. CoRR, 2026.Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrationshttps://vision.ics.uci.edu/papers/robotic-manipulation-by-imitating-generated-videos-without-physical-2025/https://vision.ics.uci.edu/papers/robotic-manipulation-by-imitating-generated-videos-without-physical-2025/Shivansh Patel, Shraddhaa Mohan, Hanlin Mai, Unnat Jain, Svetlana Lazebnik, Yunzhu Li. ICLR, 2026.Rotation Equivariant Convolutions in Deformable Registration of Brain MRIhttps://vision.ics.uci.edu/papers/rotation-equivariant-convolutions-in-deformable-registration-of-brain-2026/https://vision.ics.uci.edu/papers/rotation-equivariant-convolutions-in-deformable-registration-of-brain-2026/Arghavan Rezvani, Kun Han, Anthony T. Wu, Pooya Khosravi, Xiaohui Xie. ISBI, 2026.Unified Visuomotor Targets: Supervising VLAs Beyond Physical Actionshttps://vision.ics.uci.edu/papers/unified-visuomotor-targets-supervising-vlas-beyond-physical-actions-2026/https://vision.ics.uci.edu/papers/unified-visuomotor-targets-supervising-vlas-beyond-physical-actions-2026/Zhenyang Feng, Unnat Jain. arXiv (Cornell University), 2026.ViPRA: Video Prediction for Robot Actionshttps://vision.ics.uci.edu/papers/vipra-video-prediction-for-robot-actions-2025/https://vision.ics.uci.edu/papers/vipra-video-prediction-for-robot-actions-2025/Sandeep Routray, Hengkai Pan, Unnat Jain, Shikhar Bahl, Deepak Pathak. ICLR, 2026.VISOR: VIsual Spatial Object Reasoning for Language-driven Object Navigationhttps://vision.ics.uci.edu/papers/visor-visual-spatial-object-reasoning-for-language-driven-2026/https://vision.ics.uci.edu/papers/visor-visual-spatial-object-reasoning-for-language-driven-2026/Francesco Taioli, Shiping Yang, Sonia Raychaudhuri, Marco Cristani, Unnat Jain, Angel X. Chang. CoRR, 2026.An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixelshttps://vision.ics.uci.edu/papers/an-image-is-worth-more-than-16x16-patches-2025/https://vision.ics.uci.edu/papers/an-image-is-worth-more-than-16x16-patches-2025/Duy-Kien Nguyen, Mido Assran, Unnat Jain, Martin R. Oswald, Cees G. M. Snoek, Xinlei Chen. ICLR, 2025.GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimationhttps://vision.ics.uci.edu/papers/geodiff-geometry-guided-diffusion-for-metric-depth-estimation-2025/https://vision.ics.uci.edu/papers/geodiff-geometry-guided-diffusion-for-metric-depth-estimation-2025/Tuan Pham, Thanh-Tung Le, Xiaohui Xie, Stephan Mandt. ICCVW, 2025.GViT: Representing Images as Gaussians for Visual Recognitionhttps://vision.ics.uci.edu/papers/gvit-representing-images-as-gaussians-for-visual-recognition-2025/https://vision.ics.uci.edu/papers/gvit-representing-images-as-gaussians-for-visual-recognition-2025/Jefferson Hernandez, Ruozhen He, Guha Balakrishnan, Alexander C. Berg, Vicente Ordonez. CoRR, 2025.Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractionshttps://vision.ics.uci.edu/papers/make-the-pertinent-salient-task-relevant-reconstruction-for-2024/https://vision.ics.uci.edu/papers/make-the-pertinent-salient-task-relevant-reconstruction-for-2024/Kyungmin Kim, JB Lanier, Pierre Baldi, Charless C. Fowlkes, Roy Fox. RLC, 2025.Ouroboros: Single-Step Diffusion Models for Cycle-Consistent Forward and Inverse Renderinghttps://vision.ics.uci.edu/papers/ouroboros-single-step-diffusion-models-for-cycle-consistent-2025/https://vision.ics.uci.edu/papers/ouroboros-single-step-diffusion-models-for-cycle-consistent-2025/Shanlin Sun, Yifan Wang, Hanwen Zhang, Yifeng Xiong, Qin Ren, Ruogu Fang, Xiaohui Xie, Chenyu You. ICCV, 2025.UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesishttps://vision.ics.uci.edu/papers/umami-unifying-masked-autoregressive-models-and-deterministic-rendering-2025/https://vision.ics.uci.edu/papers/umami-unifying-masked-autoregressive-models-and-deterministic-rendering-2025/Thanh-Tung Le, Tuan Pham, Tung Nguyen, Deying Kong, Xiaohui Xie, Stephan Mandt. NeurIPS, 2025.XOCT: Enhancing OCT to OCTA Translation via Cross-Dimensional Supervised Multi-scale Feature Learninghttps://vision.ics.uci.edu/papers/xoct-enhancing-oct-to-octa-translation-via-cross-2025/https://vision.ics.uci.edu/papers/xoct-enhancing-oct-to-octa-translation-via-cross-2025/Pooya Khosravi, Kun Han, Anthony T. Wu, Arghavan Rezvani, Zexin Feng, Xiaohui Xie. MICCAI (4), 2025.