arXiv:2608. 14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools to decompose internal representations into sparse and more interpretable features.
By Philip H. Lee, Parth Padalkar
arXiv:2605.22902v2 Announce Type: replace-cross
Abstract: Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly u...
By Dimitrios Damianos, Leon Voukoutis, Georgios Skyrianos, Vassilis Katsouros, Georgios Paraskevopoulos
arXiv:2607. 07316v1 Announce Type: new Abstract: This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms of modern neural networks.
By Pranav Sawant, Jakub Krej\v{c}\'i
arXiv:2607. 08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept.
By Weiduo Liao, Yunqiao Yang, Ying Wei
arXiv:2606. 16193v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult to interpret.
By Yusong Zhao, Hengyi Wang, Tanuja Ganu, Akshay Nambi, Hao Wang
arXiv:2607. 00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact.
By Hussein Chouman, Wataru Sasaki, Tomokazu Matsui, Hirohiko Suwa, Keiichi Yasumoto