AlignSAE: Concept-Aligned Sparse Autoencoders
Minglai Yang, Xinyu Guo, Zhengliang Shi et al.
Action editor: Quanshi Zhang
@tmlr-pub.bsky.social
@tmlr-pub.bsky.socialAlignSAE: Concept-Aligned Sparse Autoencoders
Minglai Yang, Xinyu Guo, Zhengliang Shi et al.
Action editor: Quanshi Zhang
@tmlr-pub.bsky.socialA Symmetry-Matching Approach to Blind-Spot Reduction in Sparse Autoencoders
Csaba Balogh
Action editor: David Rügamer
@tmlr-pub.bsky.socialNew #Reproducibility Certification:
A Reproduction Study of Weight-Based Mechanistic Interpretability in Bilinear MLPs
Itay Erlich, May Ben Zion, Jacob Shashoua
@tmlr-pub.bsky.socialNew #J2C Certification:
Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
Marco Bronzini, Carlo Nicolini, Bruno Lepri, Jacopo Staiano, Andrea Passerini
@tmlr-pub.bsky.socialSimpleDesign: A Joint Model for Protein Sequence and Structure Codesign
Jiarui Lu, Yuyang Wang, Yizhe Zhang et al.
Action editor: Tianshu Yu
@tmlr-pub.bsky.socialThe Impact of Enforcing Representational Consistency of Identical Transformations for Disentangle...
Hee-Jun Jung, Hoyong Kim, Ilmin Kang, Kangil Kim
Action editor: Vincent Fortuin
@tmlr-pub.bsky.socialHow Much Information Fits in a Vector?
Christopher Neil Gadzinski, Decebal Constantin Mocanu
Action editor: Antoine Ledent