『Mapping visual circuits to fix AI』のカバーアート

Mapping visual circuits to fix AI

Mapping visual circuits to fix AI

無料で聴く

ポッドキャストの詳細を見る
Finding that a network encodes something is not the same as knowing how it uses it. Edge-based circuits have been defined for large language models, but work on vision models has so far only used neuron-based circuits, which show what is encoded but not how it is routed. The authors introduce Automatic Visual Circuit Discovery (Vi-CD), which finds sparse, edge-based computational subgraphs in vision transformers. They apply it to class-specific classification circuits, to the circuits behind typographic attacks on CLIP, and to circuits that can be steered to correct harmful behavior: on the RoCOCO benchmark, steering the discovered circuits reduces safety violations more than random ablations while keeping retrieval performance close to baseline. This opens the journal club's circuits series (Oct 21). Paper: https://arxiv.org/abs/2604.14477
adbl_web_anon_alc_button_suppression_t1
まだレビューはありません