Stepan Shabalin — accepted AI-conference papers

2025

Scaling Sparse Feature Circuits For Studying In-Context Learning

Dmitrii Kharlapenko, Stepan Shabalin, Arthur Conmy, Neel Nanda

ICML 2025poster

Sparse autoencoders (SAEs) are a popular tool for interpreting large language model activations, but their utility in addressing open questions in interpretability remains unclear. In this work, we demonstrate their effectiveness by using SAEs to deepen our understanding of the mechanism behind in-c…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors

Paul Steven Scotti, Atmadeep Banerjee, Jimmie Goode, Stepan Shabalin, Alex Nguyen, Cohen Ethan +6

NeurIPS 2023spotlight

We present MindEye, a novel fMRI-to-image approach to retrieve and reconstruct viewed images from brain activity. Our model comprises two parallel submodules that are specialized for retrieval (using contrastive learning) and reconstruction (using a diffusion prior). MindEye can map fMRI brain activ…

Cited by 118 Source ↗PDF ↗code ↗Scholar ↗