Safety in Multimodal Large Language Models (MLLMs) depends on unsafe multimodal data for post-training alignment or activation steering. However, such data is hard to collect, must be gathered anew fo
1 comments
Harnessing Textual Refusal Directions for Multimodal Safety was first seen on Hugging Face · Daily papers on Oct 20, 2026. Since then it appeared in 10 hourly checks across 2 days, peaking at #13 on Oct 21, 03:18 UTC. It was last on the list on Oct 21, 03:18 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Show that this trended, linking back to this page.
<a href="https://trendoday.com/hugging-face/papers/2606.31876-harnessing-textual-refusal-directions-for-multimodal-safety"><img src="https://trendoday.com/badge/hugging-face/papers/2606.31876-harnessing-textual-refusal-directions-for-multimodal-safety.svg" alt="Harnessing Textual Refusal Directions for Multimodal Safety on TrendBoard" height="44"></a>
[](https://trendoday.com/hugging-face/papers/2606.31876-harnessing-textual-refusal-directions-for-multimodal-safety)