# VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models

Authors: Junzhe Chen, Tian Qin, Eugenie Shi, Tianshu Zhang, Qiang Ju, Lijie Wen.

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: 2026-11-03.
ArXiv initial submission: 2026-11-03.

[Original paper](https://arxiv.org/abs/2611.05066) · [PDF](https://arxiv.org/pdf/2611.05066) · [HTML](https://arxiv.org/html/2611.05066v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2611.05066/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2611.05066/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2611.05066/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2611.05066/record.json)

## Approaches

- [Alternative generation methods](https://latent-implicit-thinking.github.io/topics/alternative-reasoning-schedules/): Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.

Reading-list version 0.15.2; literature checked through 2026-11-03.