Yuval Atzmon ![](/sites/default/files/person/yuval_photo%281%29.jpg) I work on generative vision models across different data modalities (like video, natural language, and action). My focus is on controllable and personalized image and video generation with fine-grained control over identity, motion, and compositional relationships. I obtained my Ph.D. under the guidance of Prof. Gal Chechik at Bar-Ilan University. My M.Sc. and B.Sc. are in Electrical Engineering from the Technion, Israel Institute of Technology. Research Area(s) [Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence) [Computer Graphics](/index.php/research-area/computer-graphics) [Computer Vision](/index.php/research-area/computer-vision) [Generative AI](/index.php/research-area/generative-ai) Main Field of Interest [Generative AI](/index.php/research-area/generative-ai) Google Scholar [https://scholar.google.com/citations?user=VJZj2MsAAAAJ&hl=en](https://scholar.google.com/citations?user=VJZj2MsAAAAJ&hl=en) ### Publications ### 2025 [Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image](/index.php/publication/2025-11_data-driven-loss-functions-inference-time-optimization-text-image) Sapir Yflah, [Yuval Atzmon](/index.php/person/yuval-atzmon), [Gal Chechik](/index.php/person/gal-chechik) [WACV 2026](https://arxiv.org/pdf/2509.02295) [Identity-Motion Trade-offs in Text-to-Video Generation](/publication/2025-07_identity-motion-trade-offs-text-video-generation) [Yuval Atzmon](/person/yuval-atzmon), Rinon Gal, [Yoad Tewel](/person/yoad-tewel), [Yoni Kasten](/person/yoni-kasten), [Gal Chechik](/person/gal-chechik) [BMVC 2025](https://bmvc2025.bmva.org/proceedings/159/) [Add-it: Training-Free Object Insertion in Images via Pretrained Diffusion Models](/publication/2025-04_add-it-training-free-object-insertion-images-pretrained-diffusion-models) [Yoad Tewel](/person/yoad-tewel), Rinon Gal, Dvir Samuel, [Yuval Atzmon](/person/yuval-atzmon), Lior Wolf, [Gal Chechik](/person/gal-chechik) [ICLR 2025](https://iclr.cc/virtual/2025/poster/29207) ### 2024 [ConsiStory: Training-Free Consistent Text-to-Image Generation](/index.php/publication/2024-02_consistory-training-free-consistent-text-image-generation) Yoad Tewel, Omri Kaduri, Rinon Gal, [Yoni Kasten](/index.php/person/yoni-kasten), Lior Wolf, [Gal Chechik](/index.php/person/gal-chechik), [Yuval Atzmon](/index.php/person/yuval-atzmon) [SIGGRAPH](https://arxiv.org/abs/2402.03286) ### 2023 [Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models](/publication/2023-12_domain-agnostic-tuning-encoder-fast-personalization-text-image-models) Moab Arar, Rinon Gal, [Yuval Atzmon](/person/yuval-atzmon), [Gal Chechik](/person/gal-chechik), Daniel Cohen-Or, Ariel Shamir, Amit Bermano [SIGGRAPH Asia 2023](https://arxiv.org/abs/2307.06925) [Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models](/publication/2023-08_encoder-based-domain-tuning-fast-personalization-text-image-models-0) Rinon Gal, Moab Arar, [Yuval Atzmon](/person/yuval-atzmon), Amit Bermano, [Gal Chechik](/person/gal-chechik), Daniel Cohen-Or [SIGGRAPH 2023](https://arxiv.org/abs/2302.12228) [Key-Locked Rank One Editing for Text-to-Image Personalization](/index.php/publication/2023-08_key-locked-rank-one-editing-text-image-personalization) Yoad Tewel, Rinon Gal, [Gal Chechik](/index.php/person/gal-chechik), [Yuval Atzmon](/index.php/person/yuval-atzmon) [SIGGRAPH 2023](https://s2023.siggraph.org/) [Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models](/publication/2023-08_encoder-based-domain-tuning-fast-personalization-text-image-models) Rinon Gal, Moab Arar, [Yuval Atzmon](/person/yuval-atzmon), Amit H. Bermano, [Gal Chechik](/person/gal-chechik), Daniel Cohen-Or [SIGGRAPH 2023](https://s2023.siggraph.org/) [Learning to Initiate and Reason in Event-Driven Cascading Processes](/index.php/publication/2023-07_learning-initiate-and-reason-event-driven-cascading-processes) [Yuval Atzmon](/index.php/person/yuval-atzmon), [Eli Meirom](/index.php/person/eli-meirom), [Shie Mannor](/index.php/person/shie-mannor), [Gal Chechik](/index.php/person/gal-chechik) [ICML 2023](https://proceedings.mlr.press/v202/atzmon23a/atzmon23a.pdf) ### 2022 ["This is my unicorn, Fluffy": Personalizing frozen vision-language representations](/index.php/publication/2022-11_my-unicorn-fluffy-personalizing-frozen-vision-language-representations) Niv Cohen, Rinon Gal, [Eli Meirom](/index.php/person/eli-meirom), [Gal Chechik](/index.php/person/gal-chechik), [Yuval Atzmon](/index.php/person/yuval-atzmon) [ECCV 2022](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136800544.pdf) [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](/publication/2022-08_image-worth-one-word-personalizing-text-image-generation-using-textual) Rinon Gal, Yuval Alaluf, [Yuval Atzmon](/person/yuval-atzmon), Or Patashnik, Amit H. Bermano, [Gal Chechik](/person/gal-chechik), Daniel Cohen-Or [ICLR 2023](https://iclr.cc/virtual/2023/oral/12700) Top 25% ["This is my unicorn, Fluffy": Personalizing frozen vision-language representations](/publication/2022-04_my-unicorn-fluffy-personalizing-frozen-vision-language-representations) Niv Cohen, Rinon Gal, [Gal Chechik](/person/gal-chechik), [Yuval Atzmon](/person/yuval-atzmon) [ECCV 2022](https://eccv2022.ecva.net/) Oral ### 2021 [Known unknowns: Learning novel concepts using exploratory reasoning-by-elimination](/publication/2021-07_known-unknowns-learning-novel-concepts-using-exploratory-reasoning-elimination) Harsh Agrawal, [Eli Meirom](/person/eli-meirom), [Yuval Atzmon](/person/yuval-atzmon), [Shie Mannor](/person/shie-mannor), [Gal Chechik](/person/gal-chechik) [ Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Inte…](https://www.auai.org/uai2021/accepted_papers) Oral [From Generalized Zero-Shot Learning to Long-Tail with Class Descriptors](/index.php/publication/2021-01_generalized-zero-shot-learning-long-tail-class-descriptors) Dvir Samuel, [Yuval Atzmon](/index.php/person/yuval-atzmon), [Gal Chechik](/index.php/person/gal-chechik) [Winter Conference on Applications of Computer Vision (WACV) 2021](http://wacv2021.thecvf.com/home) ### 2020 [A Causal View of Compositional Zero-Shot Recognition](/publication/2020-12_causal-view-compositional-zero-shot-recognition) [Yuval Atzmon](/person/yuval-atzmon), Felix Kreuk, Uri Shalit, [Gal Chechik](/person/gal-chechik) [Neural Information Processing Systems (NeurIPS) 2020 (Spotlight)](https://neurips.cc/Conferences/2020/) [ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization](/publication/2020-11_zest-zero-shot-learning-text-descriptions-using-textual-similarity-and-visual) Tzuf Paz-Argaman, [Yuval Atzmon](/person/yuval-atzmon), [Gal Chechik](/person/gal-chechik), Reut Tsarfaty [Findings of EMNLP](https://2020.emnlp.org/) ### 2019 [Joint Optimization for Cooperative Image Captioning](/index.php/publication/2019-11_joint-optimization-cooperative-image-captioning) Gilad Vered, Gal Oren, [Yuval Atzmon](/index.php/person/yuval-atzmon), [Gal Chechik](/index.php/person/gal-chechik) [International conference on computer vision (ICCV)](http://openaccess.thecvf.com/content_ICCV_2019/papers/Vered_Joint_Optimization_for_Cooperative_Image_Captioning_ICCV_2019_paper.) [Adaptive Confidence Smoothing for Generalized Zero-Shot Learning](/publication/2019-03_adaptive-confidence-smoothing-generalized-zero-shot-learning) [Yuval Atzmon](/person/yuval-atzmon), [Gal Chechik](/person/gal-chechik) Computer Vision and Pattern Recognition (CVPR) 2019 ### 2018 [Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning](/publication/2018-05_probabilistic-and-or-attribute-grouping-zero-shot-learning) [Yuval Atzmon](/person/yuval-atzmon), [Gal Chechik](/person/gal-chechik) [The conference on uncertainty in artificial intelligence (UAI 2018)](http://auai.org/uai2018/) ### 2016 [Learning to generalize to new compositions in image understanding](/publication/2016-08_learning-generalize-new-compositions-image-understanding) [Yuval Atzmon](/person/yuval-atzmon), Jonathan Berant, Vahid Kezami, Amir Globerson, [Gal Chechik](/person/gal-chechik) [Arxiv](https://arxiv.org/abs/1608.07639) ### 2015 [Learning Sparse Metrics, One Feature at a Time](/publication/2015-12_learning-sparse-metrics-one-feature-time) [Yuval Atzmon](/person/yuval-atzmon), Uri Shalit, [Gal Chechik](/person/gal-chechik) [Journal of Machine Learning Research](https://proceedings.mlr.press/v44/atzmon2015.html)