From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model

• URL: http://arxiv.org/abs/2510.19871v1
• Date: Wed, 22 Oct 2025 06:58:55 GMT
• Title: From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
• Authors: Yatai Ji, Teng Wang, Yuying Ge, Zhiheng Liu, Sidi Yang, Ying Shan, Ping Luo,
• Abstract summary: We introduce ReDiff, a refining-enhanced diffusion framework that teaches the model to identify and correct its own errors.<n>Our approach features a two-stage training process: first, we instill a foundational revision capability by training the model to revise synthetic errors; second, we implement a novel online self-correction loop.<n>This mistake-driven learning endows the model with the crucial ability to revisit and refine its already generated output, effectively breaking the error cascade.
• Score: 72.73512218682187
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Discrete diffusion models have emerged as a promising direction for vision-language tasks, offering bidirectional context modeling and theoretical parallelization. However, their practical application is severely hindered by a train-inference discrepancy, which leads to catastrophic error cascades: initial token errors during parallel decoding pollute the generation context, triggering a chain reaction of compounding errors and leading to syntactic errors and semantic hallucinations. To address this fundamental challenge, we reframe the generation process from passive denoising to active refining. We introduce ReDiff, a refining-enhanced diffusion framework that teaches the model to identify and correct its own errors. Our approach features a two-stage training process: first, we instill a foundational revision capability by training the model to revise synthetic errors; second, we implement a novel online self-correction loop where the model is explicitly trained to revise its own flawed drafts by learning from an expert's corrections. This mistake-driven learning endows the model with the crucial ability to revisit and refine its already generated output, effectively breaking the error cascade. Extensive experiments demonstrate that ReDiff significantly improves the coherence and factual accuracy of generated content, enabling stable and efficient parallel generation far superior to traditional denoising methods. Our codes and models are available at https://rediff-hku.github.io/.

Related papers

• Training-Free Self-Correction for Multimodal Masked Diffusion Models [61.84305395626145]
  We propose a training-free self-correction framework that exploits the inductive biases of pre-trained masked diffusion models.<n>Our method significantly improves generation quality on text-to-image generation and multimodal understanding tasks with reduced sampling steps.
  arXiv  Detail & Related papers  (2026-02-02T23:58:15Z)
• Teach Diffusion Language Models to Learn from Their Own Mistakes [45.68746718883178]
  Masked Diffusion Language Models (DLMs) achieve significant speed by generating multiple tokens in parallel.<n> parallel sampling approach will introduce strong dependency errors and cause quality to deteriorate rapidly as the generation step size grows.<n>We propose Decoupled Self-Correction to maintain high-quality multi-token generation.
  arXiv  Detail & Related papers  (2026-01-10T05:04:33Z)
• Corrective Diffusion Language Models [12.724100711773593]
  We study corrective behavior in diffusion language models, defined as the ability to assign lower confidence to incorrect tokens and iteratively refine them while preserving correct content.<n>We propose a correction-oriented post-training principle that explicitly supervises visible incorrect tokens, enabling error-aware confidence and targeted refinement.
  arXiv  Detail & Related papers  (2025-12-17T17:04:38Z)
• Consistent World Models via Foresight Diffusion [56.45012929930605]
  We argue that a key bottleneck in learning consistent diffusion-based world models lies in the suboptimal predictive ability.<n>We propose Foresight Diffusion (ForeDiff), a diffusion-based world modeling framework that enhances consistency by decoupling condition understanding from target denoising.
  arXiv  Detail & Related papers  (2025-05-22T10:01:59Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• Diffusing States and Matching Scores: A New Framework for Imitation Learning [16.941612670582522]
  Adversarial Imitation Learning is traditionally framed as a two-player zero-sum game between a learner and an adversarially chosen cost function.<n> diffusion models have emerged as a non-adversarial alternative to GANs that merely require training a score function via regression.<n>We show our approach outperforms both GAN-style imitation learning baselines and discriminator-free imitation learning baselines across various continuous control problems.
  arXiv  Detail & Related papers  (2024-10-17T17:59:25Z)
• ConsistencyDet: A Few-step Denoising Framework for Object Detection Using the Consistency Model [22.34776007498307]
  We introduce a novel framework designed to articulate object detection as a denoising diffusion process.<n>The framework, termed textbfConsistencyDet, leverages an innovative denoising concept known as the Consistency Model.
  arXiv  Detail & Related papers  (2024-04-11T14:08:45Z)
• PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model [37.2192243883707]
  We propose PLANNER, a model that combines latent semantic diffusion with autoregressive generation to generate fluent text. Results on semantic generation, text completion and summarization show its effectiveness in generating high-quality long-form text.
  arXiv  Detail & Related papers  (2023-06-05T01:36:39Z)
• Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning [57.4036085386653]
  We show that prompt-based models for sentence pair classification tasks still suffer from a common pitfall of adopting inferences based on lexical overlap. We then show that adding a regularization that preserves pretraining weights is effective in mitigating this destructive tendency of few-shot finetuning.
  arXiv  Detail & Related papers  (2021-09-09T10:10:29Z)
• NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models [54.184609286094044]
  We propose noise entropy regularisation (NoiER) as an efficient learning paradigm that solves the problem without auxiliary models and additional data. The proposed approach improved traditional OOD detection evaluation metrics by 55% on average compared to the original fine-tuned models.
  arXiv  Detail & Related papers  (2021-08-29T06:58:28Z)
• Factual Error Correction for Abstractive Summarization Models [41.77317902748772]
  We propose a post-editing corrector module to correct factual errors in generated summaries. We show that our model is able to correct factual errors in summaries generated by other neural summarization models. We also find that transferring from artificial error correction to downstream settings is still very challenging.
  arXiv  Detail & Related papers  (2020-10-17T04:24:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.