Yossi Gandelsman

51 papers A* 15Journal 34Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering. CoRR Yigit Ekin, Yossi Gandelsman
2025	J	`jnl`	An Empirical Study of Autoregressive Pre-training from Videos. CoRR Jathushan Rajasegaran, Ilija Radosavovic, Rahul Ravishankar, Yossi Gandelsman, Christoph Feichtenhofer, Jitendra Malik
2025	J	`jnl`	In-Context Representation Hijacking. CoRR Itay Yona, Amir Sarid, Michael Karasik, Yossi Gandelsman
2025	J	`jnl`	Interpreting ResNet-based CLIP via Neuron-Attention Decomposition. CoRR Edmund Bu, Yossi Gandelsman
2025	A*	`conf`	Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations. ICLR Nick Jiang, Anish Kachinthaya, Suzanne Petryk, Yossi Gandelsman
2025	A*	`conf`	Interpreting the Repeated Token Phenomenon in Large Language Models. ICML Itay Yona, Ilia Shumailov, Jamie Hayes, Yossi Gandelsman
2025	J	`jnl`	Interpreting the Repeated Token Phenomenon in Large Language Models. CoRR Itay Yona, Ilia Shumailov, Jamie Hayes, Federico Barbero, Yossi Gandelsman
2025	A*	`conf`	Interpreting the Second-Order Effects of Neurons in CLIP. ICLR Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt
2025	A*	`conf`	LLMs can see and hear without any training. ICML Kumar Ashutosh, Yossi Gandelsman, Xinlei Chen, Ishan Misra, Rohit Girdhar
2025	J	`jnl`	LLMs can see and hear without any training. CoRR Kumar Ashutosh, Yossi Gandelsman, Xinlei Chen, Ishan Misra, Rohit Girdhar
2025	J	`jnl`	Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs. CoRR Yaniv Nikankin, Dana Arad, Yossi Gandelsman, Yonatan Belinkov
2025	J	`jnl`	Steering CLIP's vision transformer with sparse autoencoders. CoRR Sonia Joseph, Praneet Suresh, Ethan Goldfarb, Lorenz Hufe, Yossi Gandelsman, Robert Graham, Danilo Bzdok, Wojciech Samek, Blake Aaron Richards
2025	J	`jnl`	Teaching Humans Subtle Differences with DIFFusion. CoRR Mia Chiquier, Orr Avrech, Yossi Gandelsman, Berthy Feng, Katherine L. Bouman, Carl Vondrick
2025	J	`jnl`	Test-Time Training on Video Streams. J. Mach. Learn. Res. Renhao Wang, Yu Sun, Arnuv Tandon, Yossi Gandelsman, Xinlei Chen, Alexei A. Efros, Xiaolong Wang
2025	J	`jnl`	Vision Transformers Don't Need Trained Registers. CoRR Nick Jiang, Amil Dravid, Alexei A. Efros, Yossi Gandelsman
2024	J	`jnl`	IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks. Trans. Mach. Learn. Res. Jiarui Xu, Yossi Gandelsman, Amir Bar, Jianwei Yang, Jianfeng Gao, Trevor Darrell, Xiaolong Wang
2024	A*	`conf`	Idempotent Generative Network. ICLR Assaf Shocher, Amil Dravid, Yossi Gandelsman, Inbar Mosseri, Michael Rubinstein, Alexei A. Efros
2024	A*	`conf`	Interpreting CLIP's Image Representation via Text-Based Decomposition. ICLR Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt
2024	J	`jnl`	Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations. CoRR Nick Jiang, Anish Kachinthaya, Suzie Petryk, Yossi Gandelsman
2024	J	`jnl`	Interpreting the Second-Order Effects of Neurons in CLIP. CoRR Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt
2024	A*	`conf`	Interpreting the Weight Space of Customized Diffusion Models. NeurIPS Amil Dravid, Yossi Gandelsman, Kuan-Chieh Wang, Rameen Abdal, Gordon Wetzstein, Alexei A. Efros, Kfir Aberman
2024	J	`jnl`	Interpreting the Weight Space of Customized Diffusion Models. CoRR Amil Dravid, Yossi Gandelsman, Kuan-Chieh Wang, Rameen Abdal, Gordon Wetzstein, Alexei A. Efros, Kfir Aberman
2024	J	`jnl`	Learning Video Representations without Natural Videos. CoRR Xueyang Yu, Xinlei Chen, Yossi Gandelsman
2024	J	`jnl`	Quantifying and Enabling the Interpretability of CLIP-like Models. CoRR Avinash Madasu, Yossi Gandelsman, Vasudev Lal, Phillip Howard
2024	J	`jnl`	Synthesizing Moving People with 3D Control. CoRR Boyi Li, Jathushan Rajasegaran, Yossi Gandelsman, Alexei A. Efros, Jitendra Malik
2024	A*	`conf`	The More You See in 2D, the More You Perceive in 3D. CVPR Xinyang Han, Zelin Gao, Angjoo Kanazawa, Shubham Goel, Yossi Gandelsman
2024	J	`jnl`	The More You See in 2D, the More You Perceive in 3D. CoRR Xinyang Han, Zelin Gao, Angjoo Kanazawa, Shubham Goel, Yossi Gandelsman
2023	J	`jnl`	IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks. CoRR Jiarui Xu, Yossi Gandelsman, Amir Bar, Jianwei Yang, Jianfeng Gao, Trevor Darrell, Xiaolong Wang
2023	J	`jnl`	Idempotent Generative Network. CoRR Assaf Shocher, Amil Dravid, Yossi Gandelsman, Inbar Mosseri, Michael Rubinstein, Alexei A. Efros
2023	J	`jnl`	Interpreting CLIP's Image Representation via Text-Based Decomposition. CoRR Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt
2023	J	`jnl`	Reconstruction of Patient-Specific Confounders in AI-based Radiologic Image Interpretation using Generative Pretraining. CoRR Tianyu Han, Laura Zigutyte, Luisa Huck, Marc Huppertz, Robert Siepmann, Yossi Gandelsman, Christian Blüthgen, Firas Khader, Christiane Kuhl, Sven Nebelung, Jakob Nikolas Kather, Daniel Truhn
2023	A*	`conf`	Rosetta Neurons: Mining the Common Units in a Model Zoo. ICCV Amil Dravid, Yossi Gandelsman, Alexei A. Efros, Assaf Shocher
2023	J	`jnl`	Rosetta Neurons: Mining the Common Units in a Model Zoo. CoRR Amil Dravid, Yossi Gandelsman, Alexei A. Efros, Assaf Shocher
2023	J	`jnl`	Test-Time Training on Video Streams. CoRR Renhao Wang, Yu Sun, Yossi Gandelsman, Xinlei Chen, Alexei A. Efros, Xiaolong Wang
2022	A*	`conf`	Deep Saliency Prior for Reducing Visual Distraction. CVPR Kfir Aberman, Junfeng He, Yossi Gandelsman, Inbar Mosseri, David E. Jacobs, Kai Kohlhoff, Yael Pritch, Michael Rubinstein
2022	—	`conf`	Learning A Personalized Generative Prior For Face Images. SIGGRAPH Posters Yotam Nitzan, Kfir Aberman, Orly Liba, Qiurui He, Michal Yarom, Yossi Gandelsman, Inbar Mosseri, Yael Pritch, Daniel Cohen-Or
2022	J	`jnl`	MyStyle: A Personalized Generative Prior. CoRR Yotam Nitzan, Kfir Aberman, Qiurui He, Orly Liba, Michal Yarom, Yossi Gandelsman, Inbar Mosseri, Yael Pritch, Daniel Cohen-Or
2022	J	`jnl`	MyStyle: A Personalized Generative Prior. ACM Trans. Graph. Yotam Nitzan, Kfir Aberman, Qiurui He, Orly Liba, Michal Yarom, Yossi Gandelsman, Inbar Mosseri, Yael Pritch, Daniel Cohen-Or
2022	—	`conf`	On the Effectiveness of ViT Features as Local Semantic Descriptors. ECCV Workshops (4) Shir Amir, Yossi Gandelsman, Shai Bagon, Tali Dekel
2022	A*	`conf`	Test-Time Training with Masked Autoencoders. NeurIPS Yossi Gandelsman, Yu Sun, Xinlei Chen, Alexei A. Efros
2022	J	`jnl`	Test-Time Training with Masked Autoencoders. CoRR Yossi Gandelsman, Yu Sun, Xinlei Chen, Alexei A. Efros
2022	A*	`conf`	Visual Prompting via Image Inpainting. NeurIPS Amir Bar, Yossi Gandelsman, Trevor Darrell, Amir Globerson, Alexei A. Efros
2022	J	`jnl`	Visual Prompting via Image Inpainting. CoRR Amir Bar, Yossi Gandelsman, Trevor Darrell, Amir Globerson, Alexei A. Efros
2021	J	`jnl`	Deep Saliency Prior for Reducing Visual Distraction. CoRR Kfir Aberman, Junfeng He, Yossi Gandelsman, Inbar Mosseri, David E. Jacobs, Kai Kohlhoff, Yael Pritch, Michael Rubinstein
2021	J	`jnl`	Deep ViT Features as Dense Visual Descriptors. CoRR Shir Amir, Yossi Gandelsman, Shai Bagon, Tali Dekel
2021	A*	`conf`	Explaining in Style: Training a GAN to explain a classifier in StyleSpace. ICCV Oran Lang, Yossi Gandelsman, Michal Yarom, Yoav Wald, Gal Elidan, Avinatan Hassidim, William T. Freeman, Phillip Isola, Amir Globerson, Michal Irani, Inbar Mosseri
2021	J	`jnl`	Explaining in Style: Training a GAN to explain a classifier in StyleSpace. CoRR Oran Lang, Yossi Gandelsman, Michal Yarom, Yoav Wald, Gal Elidan, Avinatan Hassidim, William T. Freeman, Phillip Isola, Amir Globerson, Michal Irani, Inbar Mosseri
2020	A*	`conf`	Semantic Pyramid for Image Generation. CVPR Assaf Shocher, Yossi Gandelsman, Inbar Mosseri, Michal Yarom, Michal Irani, William T. Freeman, Tali Dekel
2020	J	`jnl`	Semantic Pyramid for Image Generation. CoRR Assaf Shocher, Yossi Gandelsman, Inbar Mosseri, Michal Yarom, Michal Irani, William T. Freeman, Tali Dekel
2019	A*	`conf`	"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors. CVPR Yossi Gandelsman, Assaf Shocher, Michal Irani
2018	J	`jnl`	"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors. CoRR Yossi Gandelsman, Assaf Shocher, Michal Irani