Navve Wasserman

I'm a PhD student at the Weizmann Institute of Science in the Department of Computer Science, advised by Michal Irani. I am currently based in Boston, continuing my PhD and working on brain interpretability, in collaboration with Tamar Rott Shaham and Antonio Torralba from MIT.

My research focuses on machine learning, computer vision, and computational neuroscience, with an emphasis on multimodal models. My main focus is developing models and tools for modeling, exploring, and interpreting the human visual system from brain activity.

Email / Scholar / Twitter / LinkedIn

News

August 2026 — Had a great time at the three-week Brains, Minds & Machines Summer School.
August 2026 — Presented a poster and gave a contributed talk at CCN on our Universal Brain Encoder.
May 2026 — New preprint is out! Brain-IT-VQA explores visual question answering from brain activity (fMRI).
May 2026 — New preprint is out! BrainTRACE introduces an automated approach for testing visual representations in the human brain.
March 2026 — Presented BrainExplore at COSYNE 2026.
February 2026 — Functional Brain-to-Brain Transformation without Shared Stimuli was published in NeuroImage.
January 2026 — Brain-IT was accepted to ICLR 2026.

Publications

	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 arXiv, 2026 Project Page / Paper
	Brain-IT-VQA: From Brain Signals to Answers Roman Beliy, Matias Cosarinsky, Oliver Heinimann, Navve Wasserman, Michal Irani arXiv, 2026 Paper
	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 arXiv , 2026 Project Page / Paper / Demo
	Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer Roman Beliy, Amit Zalcher, Jonathan Kogman, Navve Wasserman, Michal Irani ICLR , 2026 Project Page / Paper
	The Wisdom of a Crowd of Brains: A Universal Brain Encoder Roman Beliy, Navve Wasserman, Amit Zalcher, Michal Irani CCN Proceedings, 2026 (Contributed Talk) Project Page / Paper
	Functional Brain-to-Brain Transformation without shared stimuli Navve Wasserman, Roman Beliy, Roy Urbach, Michal Irani NeuroImage, 2026 Paper
	ImpMIA: Leveraging Implicit Bias for Membership Inference under Realistic Scenarios Yuval Golbari, Navve Wasserman, Gal Vardi, Michal Irani TMLR, 2026 Project Page / Paper
	DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers Navve Wasserman, Oliver Heinimann, Yuval Golbari, Tal Zimbalist, Eli Schwartz, Michal Irani EMNLP, 2025 Project Page / Paper
	REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark Navve Wasserman, Roi Pony, Oshri Naparstek , Adi Raz Goldfarb, Eli Schwartz, Udi Barzelay, Leonid Karlinsky ACL, 2025 Project Page / Paper / Benchmark
	Don't Judge Before You CLIP: A Unified Approach for Perceptual Tasks Amit Zalcher* , Navve Wasserman, Roman Beliy, Oliver Heinimann, Michal Irani TMLR*, 2025 Project Page / Paper / Models / Demo
	Paint by Inpaint: Learning to Add Image Objects by Removing Them First Navve Wasserman, Noam Rotstein, Roy Ganz , Ron Kimmel CVPR, 2025 Project Page / Paper / Code / Dataset / Video