Stepan Shabalin

Identifiers

• name variant Stepan Shabalin 0.60 · backfill

Papers (6)

1. Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning cs.LG · 2025 · author #1
2. Patterns and Mechanisms of Contrastive Activation Engineering cs.AI · 2025 · author #3
3. Scaling sparse feature circuit finding for in-context learning cs.LG · 2025 · author #2
4. Transcoders Beat Sparse Autoencoders for Interpretability cs.LG · 2025 · author #2
5. Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs cs.CL · 2024 · author #4
6. Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors cs.CV · 2023 · author #4

Mentions

• 2505.24360 #1 · arxiv_oai · confidence 0.70 Stepan Shabalin
• 2505.03189 #3 · arxiv_oai · confidence 0.70 Stepan Shabalin
• 2504.13756 #2 · arxiv_oai · confidence 0.70 Stepan Shabalin
• 2501.18823 #2 · arxiv_oai · confidence 0.70 Stepan Shabalin
• 2404.14461 #4 · arxiv_oai · confidence 0.70 Stepan Shabalin
• 2305.18274 #4 · arxiv_oai · confidence 0.70 Stepan Shabalin

Frequent Coauthors

• Arthur Conmy 2 shared papers
• Ayush Panda 2 shared papers
• Dmitrii Kharlapenko 2 shared papers
• Yixiong Hao 2 shared papers
• Abdur Raheem Ali 1 shared papers
• Aidan J. Dempster 1 shared papers
• Alex Nguyen 1 shared papers
• Atmadeep Banerjee 1 shared papers
• David Weisberg 1 shared papers
• Elad Yundler 1 shared papers
• Ethan Cohen 1 shared papers
• Fazl Barez 1 shared papers
• Florian Tram\`er 1 shared papers
• Francesco Croce 1 shared papers
• Gon\c{c}alo Paulo 1 shared papers
• Javier Rando 1 shared papers
• Jimmie Goode 1 shared papers
• Kenneth A. Norman 1 shared papers
• Kry\v{s}tof Mitka 1 shared papers
• Maksym Andriushchenko 1 shared papers