Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models

• URL: http://arxiv.org/abs/2512.19686v1
• Date: Mon, 22 Dec 2025 18:59:03 GMT
• Title: Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models
• Authors: Zixuan Ye, Quande Liu, Cong Wei, Yuanxing Zhang, Xintao Wang, Pengfei Wan, Kun Gai, Wenhan Luo,
• Abstract summary: Chain-of-Thought (CoT) has largely improved the generation ability of unified models.<n>In this paper, we introduce visual context consistency into the reasoning of unified models.<n>We use supervised finetuning to teach the model how to plan the visual checking, conduct self-reflection and self-refinement, and use flow-GRPO to further enhance the visual consistency.
• Score: 50.87835332136393
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, the introduction of Chain-of-Thought (CoT) has largely improved the generation ability of unified models. However, it is observed that the current thinking process during generation mainly focuses on the text consistency with the text prompt, ignoring the \textbf{visual context consistency} with the visual reference images during the multi-modal generation, e.g., multi-reference generation. The lack of such consistency results in the failure in maintaining key visual features (like human ID, object attribute, style). To this end, we integrate the visual context consistency into the reasoning of unified models, explicitly motivating the model to sustain such consistency by 1) Adaptive Visual Planning: generating structured visual check list to figure out the visual element of needed consistency keeping, and 2) Iterative Visual Correction: performing self-reflection with the guidance of check lists and refining the generated result in an iterative manner. To achieve this, we use supervised finetuning to teach the model how to plan the visual checking, conduct self-reflection and self-refinement, and use flow-GRPO to further enhance the visual consistency through a customized visual checking reward. The experiments show that our method outperforms both zero-shot unified models and those with text CoTs in multi-modal generation, demonstrating higher visual context consistency.

Related papers

• Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs [60.93949629734977]
  We propose Visual Contrastive Self-Taught Reasoner (VC-STaR) to mitigate hallucinations in model-generated rationales.<n>We collect a diverse suite of VQA datasets, curate contrastive pairs according to multi-modal similarity, and generate rationales using VC-STaR.<n>Extensive experiments show that VC-STaR not only outperforms existing self-improving approaches but also surpasses models finetuned on the SoTA visual reasoning datasets.
  arXiv  Detail & Related papers  (2026-03-03T03:18:31Z)
• Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation [63.042451267669485]
  We propose Prompt Redesign for Inference-time Scaling, a framework that adaptively revises the prompt during inference in response to scaled visual generations.<n>We introduce a new verifier, element-level factual correction, which evaluates the alignment between prompt attributes and generated visuals at a fine-grained level.<n>Experiments on both text-to-image and text-to-video benchmarks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-12-03T07:54:05Z)
• ID-Consistent, Precise Expression Generation with Blendshape-Guided Diffusion [40.50436862878818]
  We present a diffusion-based framework that faithfully reimagines any subject under any particular facial expression.<n>Our adapter generalizes beyond basic emotions to subtle micro-expressions and expressive transitions, overlooked by prior works.<n>In addition, a pluggable Reference Adapter enables expression editing in real images by transferring the appearance from a reference frame during synthesis.
  arXiv  Detail & Related papers  (2025-10-06T11:20:56Z)
• Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation [120.23172120151821]
  We propose a novel approach for disentangling visual and semantic features from the backbones of pre-trained diffusion models.<n>We introduce an automated pipeline that constructs image pairs with annotated semantic and visual correspondences.<n>We propose a new metric, Visual Semantic Matching, that quantifies visual inconsistencies in subject-driven image generation.
  arXiv  Detail & Related papers  (2025-09-26T07:11:55Z)
• FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation [55.01077993490845]
  Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling.<n>We introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework.
  arXiv  Detail & Related papers  (2025-06-20T07:46:40Z)
• VSC: Visual Search Compositional Text-to-Image Diffusion Model [15.682990658945682]
  We introduce a novel compositional generation method that leverages pairwise image embeddings to improve attribute-object binding.<n>Our approach decomposes complex prompts into sub-prompts, generates corresponding images, and computes visual prototypes that fuse with text embeddings to enhance representation.<n>Our approaches outperform existing compositional text-to-image diffusion models on the benchmark T2I CompBench, achieving better image quality, evaluated by humans, and emerging robustness under scaling number of binding pairs in the prompt.
  arXiv  Detail & Related papers  (2025-05-02T08:31:43Z)
• Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Models [20.19571676239579]
  We introduce a novel diffusion-based framework to enhance the alignment of generated images with their corresponding descriptions. Our framework is built upon a comprehensive analysis of inconsistency phenomena, categorizing them based on their manifestation in the image. We then integrate a state-of-the-art controllable image generation model with a visual text generation module to generate an image that is consistent with the original prompt.
  arXiv  Detail & Related papers  (2024-06-24T06:12:16Z)
• Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement [102.22911097049953]
  Large vision-language models (LVLMs) have achieved impressive results in visual question-answering and reasoning tasks.<n>Existing methods often depend on external models or data, leading to uncontrollable and unstable alignment results.<n>We propose SIMA, a self-improvement framework that enhances visual and language modality alignment without external dependencies.
  arXiv  Detail & Related papers  (2024-05-24T23:09:27Z)
• Calibrated Self-Rewarding Vision Language Models [27.686545023186852]
  Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image. We propose the Calibrated Self-Rewarding (CSR) approach, which enables the model to self-improve by iteratively generating candidate responses, evaluating the reward for each response, and curating preference data for fine-tuning.
  arXiv  Detail & Related papers  (2024-05-23T14:30:33Z)
• Object-Attribute Binding in Text-to-Image Generation: Evaluation and Control [58.37323932401379]
  Current diffusion models create images given a text prompt as input but struggle to correctly bind attributes mentioned in the text to the right objects in the image. We propose focused cross-attention (FCA) that controls the visual attention maps by syntactic constraints found in the input sentence. We show substantial improvements in T2I generation and especially its attribute-object binding on several datasets.
  arXiv  Detail & Related papers  (2024-04-21T20:26:46Z)
• Vision-Enhanced Semantic Entity Recognition in Document Images via Visually-Asymmetric Consistency Learning [19.28860833813788]
  Existing models commonly train a visual encoder with weak cross-modal supervision signals. We propose a novel textbfVisually-textbfAsymmetric cotextbfNsistentextbfCy textbfLearning (textscVancl) approach to capture fine-grained visual and layout features.
  arXiv  Detail & Related papers  (2023-10-23T10:37:22Z)
• LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model [55.20469538848806]
  LeftRefill is an innovative approach to harness large Text-to-Image (T2I) diffusion models for reference-guided image synthesis. This paper introduces LeftRefill, an innovative approach to efficiently harness large Text-to-Image (T2I) diffusion models for reference-guided image synthesis.
  arXiv  Detail & Related papers  (2023-05-19T10:29:42Z)

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.