Enhanced Text-to-Image Generation by Fine-grained Multimodal Reasoning

• URL: http://arxiv.org/abs/2604.13491v2
• Date: Thu, 16 Apr 2026 04:19:42 GMT
• Title: Enhanced Text-to-Image Generation by Fine-grained Multimodal Reasoning
• Abstract summary: Fine-grained Multimodal Reasoning (FiMR) is a framework that leverages visual question answering (VQA) to generate explicit, fine-grained feedback.<n>FiMR consistently outperforms image generation baselines, including reasoning-based methods.
• Score: 13.412268665909826
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the rapid progress of Multimodal Large Language Models (MLLMs), unified MLLMs that jointly perform image understanding and generation have advanced significantly. However, despite the inherent reasoning capabilities of unified MLLMs for self-reflection and self-refinement, their use in text-to-image generation remains largely underexplored. Meanwhile, existing multimodal reasoning-based image generation methods mostly rely on holistic image-text alignment judgments, without fine-grained reflection and refinement of detailed prompt attributes, leading to limited fine-grained control. Therefore, we propose Fine-grained Multimodal Reasoning (FiMR), a framework that leverages decomposed visual question answering (VQA) to break down an input prompt into minimal semantic units-such as entities and attributes-and verify each unit via VQA to generate explicit, fine-grained feedback. Based on this feedback, FiMR then applies targeted, localized refinements. This fine-grained self-reasoning and self-refinement enable MLLMs to achieve more precise improvements in image-prompt alignment and overall generation quality at test time. Extensive experiments demonstrate that FiMR consistently outperforms image generation baselines, including reasoning-based methods, particularly on compositional text-to-image benchmarks. The code and models are available at https://github.com/KU-AGI/FiMR

Related papers

• Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement [50.97806700110183]
  Failure-informed Image Self-Augmentation (textbfFISA) is a framework for MLLM self-improvement that constructs augmented images from the model's own failure cases.<n>Our method generates visually challenging yet answer-preserving image complications, verifies their utility through self-examination, and applies dual fidelity filtering to avoid semantic distortion.
  arXiv  Detail & Related papers  (2026-08-04T14:28:42Z)
• Evaluation-Verification Reward for Consistent Multi-Reference Image Editing [40.370544121781144]
  Multi-dimensional Evaluation-Verification Reward(EVR)<n>EVR decomposes evaluation into distinct visual criteria.<n>Verifier grounds each claim in concrete visual evidence to accept or reject it.
  arXiv  Detail & Related papers  (2026-07-31T04:54:20Z)
• MCoT-MVS: Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning for Composed Image Retrieval [23.52156477012636]
  Composed Image Retrieval (CIR) aims to retrieve target images based on a reference image and modified texts.<n>We propose a novel Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning (MCoT-MVS) for CIR.
  arXiv  Detail & Related papers  (2026-03-18T04:49:19Z)
• Growing Visual Generative Capacity for Pre-Trained MLLMs [60.826355079902505]
  Bridge is a pure autoregressive unified MLLM that augments pre-trained visual understanding models with generative ability.<n>We propose a semantic-to-pixel discrete representation that integrates compact semantic tokens with fine-grained pixel tokens.
  arXiv  Detail & Related papers  (2025-10-02T00:40:02Z)
• MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning [75.76032840813828]
  We propose MILR, a test-time method that jointly reasons over image and text in a unified latent vector space.<n>We instantiate MILR within the unified multimodal understanding and generation framework.<n>We evaluate MILR on GenEval, T2I-CompBench, and WISE, achieving state-of-the-art results on all benchmarks.
  arXiv  Detail & Related papers  (2025-09-26T14:06:10Z)
• MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation [15.148267809916002]
  We introduce MM-R1, a framework that integrates a cross-modal Chain-of-Thought (X-CoT) reasoning strategy to unlock the inherent potential of unified MLLMs for personalized image generation.<n> Specifically, we structure personalization as an integrated visual reasoning and generation process.<n>Experiments demonstrate that MM-R1 unleashes the personalization capability of unified MLLMs to generate images with high subject fidelity and strong text alignment.
  arXiv  Detail & Related papers  (2025-08-15T12:20:27Z)
• Multimodal LLMs as Customized Reward Models for Text-to-Image Generation [60.164968941945645]
  We introduce LLaVA-Reward, an efficient reward model designed to automatically evaluate text-to-image (T2I) generations across multiple perspectives.<n>LLaVA-Reward directly utilizes the hidden states of multimodal large language models (MLLMs)<n>We train LLaVA-Reward on four evaluation perspectives: text-image alignment, fidelity/artifact, safety, and overall ranking.
  arXiv  Detail & Related papers  (2025-07-28T23:52:53Z)
• Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback [33.127607245587576]
  We introduce a framework that enables MLLMs to learn complex visual reasoning from only raw images.<n>We demonstrate that this relative ease provides an ideal reward signal for optimization via Reinforcement Learning.<n>The RRVF-trained model not only outperforms existing MLLMs and supervised fine-tuning baselines but also exhibits superior generalization.
  arXiv  Detail & Related papers  (2025-07-28T12:21:19Z)
• M3-AGIQA: Multimodal, Multi-Round, Multi-Aspect AI-Generated Image Quality Assessment [65.3860007085689]
  M3-AGIQA is a comprehensive framework that enables more human-aligned, holistic evaluation of AI-generated images.<n>By aligning model outputs more closely with human judgment, M3-AGIQA delivers robust and interpretable quality scores.
  arXiv  Detail & Related papers  (2025-02-21T03:05:45Z)
• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.<n>We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.<n>We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage [50.84150600032693]
  Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations.<n>We propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions.<n>Our proposed method significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V.
  arXiv  Detail & Related papers  (2024-12-20T01:37:22Z)

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.