VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models
Chooses which masked positions to fill by comparing predictions with and without the image. Committing visually supported tokens earlier reduces hallucination during multimodal diffusion decoding.
First public: · Added to this list: November 9, 2026
Explore this approach
Alternative generation methods — Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.