Tamar Rott Shaham

I am an assistant professor at the Faculty of Mathematics and Computer Science at Weizmann Institute of Science. Before that I was a postdoctoral fellow with Antonio Torralba at CSAIL, MIT. I did my PhD at the Electrical & Computer Engineering faculty of the Technion where I worked with Tomer Michaeli.

My research interests focus on understanding, controlling, and enhancing AI models across language, vision, and multimodal settings. I develop methods to discover and explain the internal mechanisms underlying model behavior, including automated approaches that scale interpretability. My goal is to use these insights to design interventions that control model behavior, improve performance, and prevent undesired outcomes. I am also excited about using interpretability for scientific discovery, uncovering new hypotheses and scientific insights from the knowledge encoded in models trained on scientific data.

I am actively looking for students and postdoctoral researchers to join my group. If you are interested in interpretability, multimodal AI, AI for scientific discovery, or related questions, please get in touch.

Office: 259 Jacob Ziskind Building

Email / Google Scholar / Twitter / Github

News

[Sep 2026] I joined the Weizmann Institute of Science as an Assistant Professor. I'm recruiting excellent students and postdocs; if you're interested, please reach out by email.

[Aug 2026] Joined the organizing committee of the New England Mechanistic Interpretability workshop. It was great to see everyone! Goodbye New England.

[Jul 2026] Invited talks on "Vision or Language? On the Roles of Modalities in Multimodal Models" at Goodfire, Harvard, and Brown

[Jun 2026] Come join us at the How Do Vision Models Work? workshop at CVPR'26!

[Jan 2026] Belief tracking was accepted to ICLR!

[Dec 2025] Flying to San Diego to present four papers at NeurIPS

[Sep 2025] SAIA was accepted to Neurips!

[Sep 2025] Guest lecturer, Advanced Topics in Computer Vision, University of Michigan

[Aug 2025] Invited talk, "Can Language Models Interpret Humans?", at the New England Mechanistic Interpretability workshop

[Jun 2025] Looking forward to see everyone at the Mechanistic Interpretability for Vision workshop at CVPR'25!

[Jun 2025] Attended the CHAI workshop in California

[Jan 2025] Invited talk at the Oxford Mechanistic Interpretability Seminar

[Nov 2024] Invited talks on "Automated Interpretability Agent" at Stanford, Berkeley, Columbia, and Cornell-Tech

[Sep 2024] Flying to Milan for an invited talk at the ECCV EVAL-FoMo workshop; also gave talks at MIT's Ask the Experts, AWS's Responsible AI Team, Google Research, and IBM Research Zurich

[Jul 2024] Flying to Vienna to present MAIA at ICML

[Jun 2024] Guest lecture at Deep Learning for AI and Computer Vision, MIT Professional Education

[Jun 2024] Presented "A Vision Check-up for Language Models" at CVPR

Publications

	Text-to-Image Models Need Less from Text Encoders Than You Think Nurit Spingarn, Noa Cohen, Tamar Rott Shaham, Tomer Michaeli Preprint, 2026 arxiv
	Vision-Language Binding in In-Context Image Generation Chris Ge, Rohit Gandikota, Antonio Torralba, Tamar Rott Shaham Preprint, 2026 arxiv / web
	From Activation to Specificity: Automating Counterfactual Testing of Visual Representations in the Human Brain Yuval Golbari, Navve Wasserman, Matias Cosarinsky, Roman Beliy, Aude Oliva, Antonio Torralba, Michal Irani, Tamar Rott Shaham Preprint, 2026 arxiv / web
	Letting the Neural Code Speak: Automated Characterization of Monkey Visual Neurons Through Human Language Vedang Lad, Katrin Franke, Tamar Rott Shaham, Surya Ganguli, Andreas Tolias, Sophia Sanborn, Nikos Karantzas Preprint, 2026 arxiv / web
	The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models Kelly Cui, Nikhil Prakash, Shoval Messica, Ayush Raina, David Bau, Antonio Torralba, Tamar Rott Shaham Preprint, 2026 arxiv / web / code
	Pitfalls in Evaluating Interpretability Agents Tal Haklay, Nikhil Prakash, Sana Pandey, Antonio Torralba, Aaron Mueller, Jacob Andreas, Tamar Rott Shaham, Yonatan Belinkov BlackboxNLP, 2026 arxiv
	Agents of Chaos Natalie Shapira, Chris Wendler, Avery Yen, Gabriele Sarti, Koyena Pal, Olivia Floody, Adam Belfki, Alex Loftus, Aditya Ratan Jannali, Nikhil Prakash, Jasmine Cui, Giordano Rogers, Jannik Brinkmann, Can Rager, Amir Zur, Michael Ripa, Aruna Sankaranarayanan, David Atkinson, Rohit Gandikota, Jaden Fiotto-Kaufman, EunJeong Hwang, Hadas Orgad, P Sam Sahil, Negev Taglicht, Tomer Shabtay, Atai Ambus, Nitay Alon, Shiri Oron, Ayelet Gordon-Tapiero, Yotam Kaplan, Vered Shwartz, Tamar Rott Shaham, Christoph Riedl, Reuth Mirsky, Maarten Sap, David Manheim, Tomer Ullman, David Bau Preprint, 2026 arxiv / web
	BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain Navve Wasserman, Matias Cosarinsky, Yuval Golbari, Aude Oliva, Antonio Torralba, Tamar Rott Shaham, Michal Irani Preprint, 2025 arxiv / web
	Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent Christy Li, Josep Lopez Camuñas, Jake Thomas Touchet, Jacob Andreas, Agata Lapedriza, Antonio Torralba, Tamar Rott Shaham NeurIPS, 2025 arxiv
	It's Owl in the Numbers: Token Entanglement in Subliminal Learning Amir Zur, Zhuofan Ying, Anna Russell Loftus, Kerem Şahin, Steven Yu, Lucia Quirke, Tamar Rott Shaham, Hadas Orgad, David Bau Mechanistic Interpretability Workshop, NeurIPS, 2025 web / code
	Language Models use Lookbacks to Track Beliefs Nikhil Prakash, Natalie Shapira, Arnab Sen Sharma, Christoph Riedl, Yonatan Belinkov, Tamar Rott Shaham, David Bau, Atticus Geiger ICLR, 2026 arxiv / web / code
	SketchAgent: Language-Driven Sequential Sketch Generation Yael Vinker, Tamar Rott Shaham, Kristine Zheng, Alex Zhao, Judith E Fan, Antonio Torralba CVPR, 2025 paper / web / code
	A Multimodal Automated Interpretability Agent Tamar Rott Shaham, Sarah Schwettmann, Franklin Wang, Achyuta Rajaram, Evan Hernandez, Jacob Andreas, Antonio Torralba ICML, 2024 paper / web / code / experiment browser
	Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking Nikhil Prakash, Tamar Rott Shaham, Tal Haklay, Yonatan Belinkov, David Bau ICLR, 2024 paper / web / code
	A Vision Check-up for Language Models Pratyusha Sharma, Tamar Rott Shaham*, Manel Baradad, Stephanie Fu, Adrián Rodríguez-Muñoz, Shivam Duggal, Phillip Isola, Antonio Torralba CVPR, 2024 Highlight paper* paper / web
	FIND: A Function Interpretation Benchmark for Evaluating Interpretability Methods Sarah Schwettmann, Tamar Rott Shaham*, Joanna Materzynska, Neil Chowdhury, Shuang Li, Jacob Andreas, David Bau, Antonio Torralba NeurIPS*, 2023 paper / web / code
	Discovering Variable Binding Circuitry with Desiderata Xander Davies, Max Nadeau, Nikhil Prakash, Tamar Rott Shaham, David Bau ICML Workshop Deployable Generative AI*, 2023 paper / web / code
	Automation in Interior Space Planning: Utilizing Conditional Generative Adversarial Network Models to Create Furniture Layouts Hanan Tanasra, Tamar Rott Shaham, Tomer Michaeli Guy Austern, Shany Barath Buildings, 2023 paper
	Internal Diverse Image Completion Noa Alkobi, Tamar Rott Shaham, Tomer Michaeli CVPR, Generative Models for Computer Vision Workshop, 2023 paper
	BlendGAN: Learning and Blending the Internal Distributions of Single Images by Spatial Image-Identity Conditioning Idan Kligvasser, Tamar Rott Shaham, Noa Alkobi, Tomer Michaeli Arxiv, 2022 paper
	GANs Spatial Control via Inference-Time Adaptive Normalization Karin Jakoel, Liron Efraim, Tamar Rott Shaham WACV, 2022 paper / video / supplementals
	Catch-A-Waveform: Learning to Generate Audio from a Single Short Example Gal Greshler, Tamar Rott Shaham, Tomer Michaeli NeurIPS, 2021 paper / web / code / supplementals
	Deep Self-Dissimilarities as Powerful Visual Fingerprints Idan Kligvasser, Tamar Rott Shaham, Yuval Bahat, Tomer Michaeli NeurIPS, 2021 Spotlight presentation paper / supplementals
	Spatially-Adaptive Pixelwise Networks for Fast Image Translation Tamar Rott Shaham, Michaël Gharbi, Richard Zhang, Eli Shechtman, Tomer Michaeli CVPR, 2021 project page / arXiv
	SinGAN: Learning a generative model from a single natural image Tamar Rott Shaham, Tali Dekel, Tomer Michaeli ICCV, 2019 Best Paper Award (Marr Prize) project page / arXiv / CVF / supp / code / ICCV talk / Israel Vision Day talk (recommended)
	Deformation Aware image Compression Tamar Rott Shaham, Tomer Michaeli CVPR, 2018 Spotlight presentation project page / paper / code / spotlight
	xUnit: Learning a Spatial Activation Function for Efficient Image Restoration Idan Kligvasser, Tamar Rott Shaham, Tomer Michaeli CVPR, 2018 Spotlight presentation paper / code / spotlight (by Idan)
	Visualizing Image Priors Tamar Rott Shaham, Tomer Michaeli ECCV, 2016 project page / paper / poster
	Edge Preserving Multi-Modal Registration Based On Gradient Intensity Self-Similarity Tamar Rott Shaham, Dorin Shriki, Tamir Bendory IEEEI, 2014 paper

Wonder about the meaning of ?

This website is based on Jon Barron's template (source code)