从去噪到精炼:一种用于视觉-语言扩散模型的校正框架
From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
AI总结:
针对离散扩散模型在视觉-语言任务中的错误级联问题,提出ReDiff校正框架,通过两阶段训练和在线自我纠正循环,将生成从去噪转为精炼,显著提升连贯性与事实准确性。
摘要:
离散扩散模型已成为视觉-语言任务的一个有前景的方向,提供了双向上下文建模和理论上的并行化优势。然而,其实际应用受到训练-推理不一致性的严重阻碍,这种不一致性导致灾难性的错误级联:并行解码过程中的初始令牌错误污染了生成上下文,引发复合错误的连锁反应,并导致句法错误和语义幻觉。为了解决这一根本性挑战,我们将生成过程从被动去噪重新构建为主动精炼。我们引入了ReDiff,一个精炼增强的扩散框架,教会模型识别并纠正自身的错误。我们的方法具有两阶段的训练过程:首先,通过训练模型修正合成错误来灌输基础修订能力;其次,我们实现了一种新颖的在线自我纠正循环,其中模型通过从专家的纠正中学习,被明确训练以修订其自身有缺陷的草稿。这种基于错误驱动的学习赋予模型重新审视和精炼其已生成输出的关键能力,有效打破错误级联。大量实验表明,ReDiff显著提高了生成内容的连贯性和事实准确性,实现了稳定高效的并行生成,远优于传统的去噪方法。我们的代码和模型可在https://rediff-hku.github.io/获取。
英文摘要:
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/.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。