RIV: Recursive Introspection Mask Diffusion Vision Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, YuQian, Qiao, Limeng, Ma, Lin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914061566869504
author Li, YuQian
Qiao, Limeng
Ma, Lin
author_facet Li, YuQian
Qiao, Limeng
Ma, Lin
contents Mask Diffusion-based Vision Language Models (MDVLMs) have achieved remarkable progress in multimodal understanding tasks. However, these models are unable to correct errors in generated tokens, meaning they lack self-correction capability. In this paper, we propose Recursive Introspection Mask Diffusion Vision Language Model (RIV), which equips the model with self-correction ability through two novel mechanisms. The first is Introspection Training, where an Introspection Model is introduced to identify errors within generated sequences. Introspection Training enables the model to detect not only grammatical and spelling mistakes, but more importantly, logical errors. The second is Recursive Inference. Beginning with the standard unmasking step, the learned Introspection Model helps to identify errors in the output sequence and remask them. This alternating ($\text{unmask}\rightarrow\text{introspection}\rightarrow\text{remask}$) process is repeated recursively until reliable results are obtained. Experimental results on multiple benchmarks demonstrate that the proposed RIV achieves state-of-the-art performance, outperforming most existing MDVLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23625
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RIV: Recursive Introspection Mask Diffusion Vision Language Model
Li, YuQian
Qiao, Limeng
Ma, Lin
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Mask Diffusion-based Vision Language Models (MDVLMs) have achieved remarkable progress in multimodal understanding tasks. However, these models are unable to correct errors in generated tokens, meaning they lack self-correction capability. In this paper, we propose Recursive Introspection Mask Diffusion Vision Language Model (RIV), which equips the model with self-correction ability through two novel mechanisms. The first is Introspection Training, where an Introspection Model is introduced to identify errors within generated sequences. Introspection Training enables the model to detect not only grammatical and spelling mistakes, but more importantly, logical errors. The second is Recursive Inference. Beginning with the standard unmasking step, the learned Introspection Model helps to identify errors in the output sequence and remask them. This alternating ($\text{unmask}\rightarrow\text{introspection}\rightarrow\text{remask}$) process is repeated recursively until reliable results are obtained. Experimental results on multiple benchmarks demonstrate that the proposed RIV achieves state-of-the-art performance, outperforming most existing MDVLMs.
title RIV: Recursive Introspection Mask Diffusion Vision Language Model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2509.23625