8 citations · 20 across the 18 of their papers we have counts for
23 papers
Harmonic Representations in Symbolic Music Transformers are Localized and Controllable
Adi Silberschein, Megan Wei, Tamar Rott Shaham
Transformer models trained on symbolic music have become remarkably capable. However, it is yet unclear how they represent music structure, and whether understanding their internal…
Text-to-Image Models Need Less from Text Encoders Than You Think
Nurit Spingarn, Noa Cohen, Tamar Rott Shaham +1
Text-to-image models rely on text prompts as their primary interface to human intent. Prompts are encoded by a text encoder into embeddings that condition the image generation proc…
Vision-Language Binding in In-Context Image Generation
Chris Ge, Rohit Gandikota, Antonio Torralba +1
In-context image generation models such as FLUX.2 take a text prompt and an optional reference image as visual conditioning for the output. Internally, all three inputs -- text, re…
Letting the neural code speak: Automated characterization of monkey visual neurons through human language
Vedang Lad, Katrin Franke, Tamar Rott Shaham +4
Understanding what individual neurons encode is a core question in neuroscience. In primary visual cortex (V1), mathematical models (e.g., Gabor functions) capture neural selectivi…
From Activation to Specificity: Automating Counterfactual Testing of Visual Representations in the Human Brain
Yuval Golbari, Navve Wasserman, Matias Cosarinsky +5
Identifying which brain regions represent a visual concept in the human brain is a central challenge in neuroscience. Existing approaches have localized coarse functional regions (…
Pitfalls in Evaluating Interpretability Agents
Tal Haklay, Nikhil Prakash, Sana Pandey +5
Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverag…
The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models
Kelly Cui, Nikhil Prakash, Shoval Messica +4
Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to bind objects with their properties and spatial relations. Ye…
Agents of Chaos
Natalie Shapira, Chris Wendler, Avery Yen +35
We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord acc…
BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain
Navve Wasserman, Matias Cosarinsky, Yuval Golbari +4
Understanding how the human brain represents visual concepts, and in which brain regions these representations are encoded, remains a long-standing challenge. Decades of work have…
Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent
Christy Li, Josep Lopez Camuñas, Jake Thomas Touchet +4
When a vision model performs image recognition, which visual attributes drive its predictions? Detecting unintended reliance on specific visual features is critical for ensuring mo…
Language Models use Lookbacks to Track Beliefs
Nikhil Prakash, Natalie Shapira, Arnab Sen Sharma +5
How do language models (LMs) represent characters' beliefs, especially when those beliefs may differ from reality? This question lies at the heart of understanding the Theory of Mi…
SketchAgent: Language-Driven Sequential Sketch Generation
Yael Vinker, Tamar Rott Shaham, Kristine Zheng +3
Sketching serves as a versatile tool for externalizing ideas, enabling rapid exploration and visual communication that spans various disciplines. While artificial systems have driv…
A Multimodal Automated Interpretability Agent
Tamar Rott Shaham, Sarah Schwettmann, Franklin Wang +4
This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpr…
Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
Nikhil Prakash, Tamar Rott Shaham, Tal Haklay +2
Fine-tuning on generalized tasks such as instruction following, code generation, and mathematics has been shown to enhance language models' performance on a range of tasks. Neverth…
A Vision Check-up for Language Models
Pratyusha Sharma, Tamar Rott Shaham, Manel Baradad +5
What does learning to model relationships between strings teach large language models (LLMs) about the visual world? We systematically evaluate LLMs' abilities to generate and reco…
FIND: A Function Description Benchmark for Evaluating Interpretability Methods
Sarah Schwettmann, Tamar Rott Shaham, Joanna Materzynska +5
Labeling neural network submodules with human-legible descriptions is useful for many downstream tasks: such descriptions can surface failures, guide interventions, and perhaps eve…
Discovering Variable Binding Circuitry with Desiderata
Xander Davies, Max Nadeau, Nikhil Prakash +2
Recent work has shown that computation in language models may be human-understandable, with successful efforts to localize and intervene on both single-unit features and input-outp…
BlendGAN: Learning and Blending the Internal Distributions of Single Images by Spatial Image-Identity Conditioning
Idan Kligvasser, Tamar Rott Shaham, Noa Alkobi +1
Training a generative model on a single image has drawn significant attention in recent years. Single image generative methods are designed to learn the internal patch distribution…
Catch-A-Waveform: Learning to Generate Audio from a Single Short Example
Gal Greshler, Tamar Rott Shaham, Tomer Michaeli
Models for audio generation are typically trained on hours of recordings. Here, we illustrate that capturing the essence of an audio source is typically possible from as little as…
Spatially-Adaptive Pixelwise Networks for Fast Image Translation
Tamar Rott Shaham, Michael Gharbi, Richard Zhang +2
We introduce a new generator architecture, aimed at fast and efficient high-resolution image-to-image translation. We design the generator to be an extremely lightweight function o…
SinGAN: Learning a Generative Model from a Single Natural Image
Tamar Rott Shaham, Tali Dekel, Tomer Michaeli
We introduce SinGAN, an unconditional generative model that can be learned from a single natural image. Our model is trained to capture the internal distribution of patches within…
Deformation Aware Image Compression
Tamar Rott Shaham, Tomer Michaeli
Lossy compression algorithms aim to compactly encode images in a way which enables to restore them with minimal error. We show that a key limitation of existing algorithms is that…
xUnit: Learning a Spatial Activation Function for Efficient Image Restoration
Idan Kligvasser, Tamar Rott Shaham, Tomer Michaeli
In recent years, deep neural networks (DNNs) achieved unprecedented performance in many low-level vision tasks. However, state-of-the-art results are typically achieved by very dee…