FIELD NOTES TOPIC
safety in ai
2 notes, newest first.
Harnessing Textual Refusal Directions for Multimodal Safety
Researchers propose a new approach called Modality-Agnostic Refusal Steering (MARS) to improve safety in Multimodal Large Language Models without requiring unsafe multimodal data. MARS uses textual refusal directions…
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
The authors propose a method for safe image generation using autoregressive unified multimodal models. They introduce Iterative Self-Improving Codebooks to eliminate harmful mappings in the codebook that could generate…
