Training-free mechanistic interpretability locates lexical-encoding attention heads in ViT and shows that targeted interventions on them improve robustness to typographic attacks in CLIP and downstream LVLMs.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
IPPg embeds text into images to reduce multimodal model inference costs by 35.8-91% with competitive accuracy on many VQA and code benchmarks.
citing papers explorer
-
Towards Robustness against Typographic Attack with Training-free Concept Localization
Training-free mechanistic interpretability locates lexical-encoding attention heads in ViT and shows that targeted interventions on them improve robustness to typographic attacks in CLIP and downstream LVLMs.
-
Token-Efficient Multimodal Reasoning via Image Prompt Packaging
IPPg embeds text into images to reduce multimodal model inference costs by 35.8-91% with competitive accuracy on many VQA and code benchmarks.