Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

Item #:

085713-3202

Details

DOI: https://doi.org/10.52202/085713-3202
Author(s): Mateusz Pach, Shyamgopal Karthik, Quentin Bouniot, Serge Belongie, Zeynep Akata
Pages: 106111-106147 (37 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/085713-3202
Author(s): Mateusz Pach, Shyamgopal Karthik, Quentin Bouniot, Serge Belongie, Zeynep Akata
Pages: 106111-106147 (37 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)