Researchers introduced Modality-Agnostic Refusal Steering (MARS), a method that uses text-based refusal strategies to enhance safety in multimodal language models without requiring unsafe multimodal d…
The most upvoted papers on Hugging Face on June 26, 2026, reveal three major AI trends: smarter agents, more flexible image/video generation models, and more efficient multimodal representations. Nota…
Researchers propose DocArena, a fully automated pipeline that transforms raw document collections into controllable training environments for document search agents, using multimodal large language mo…
Researchers have developed ICG, a framework that uses multimodal large language models and personalized preference alignment to generate cover images tailored to individual users. The system extracts …