mlsanityData to 14 Oct 2026

VisuCraft: Enhancing Large Vision-Language Models for Complex Visual-Guided Creative Content Generation via Structured Information Extraction

arXiv 2508.02890 ↗First posted 4 Aug 2025cs.CV cs.CLcited by 0

On the map: Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning

Abstract (arXiv)

This paper introduces VisuCraft, a novel framework designed to significantly enhance the capabilities of Large Vision-Language Models (LVLMs) in complex visual-guided creative content generation. Existing LVLMs often exhibit limitations in maintaining high visual fidelity, genuine creativity, and precise adherence to nuanced user instructions when generating long-form texts. VisuCraft addresses these challenges by integrating a multimodal structured information extractor (E) and a dynamic prompt generation module (G). The extractor distills fine-grained visual attributes from input images into a rich, structured representation, which the dynamic prompt module then combines with user instructions to create highly optimized prompts for underlying LVLMs (e.g., LLaVA, InstructBLIP). Evaluated on the self-constructed ImageStoryGen-500K dataset using VisuGen Metrics (Visual Grounding, Creativity, and Instruction Adherence), VisuCraft consistently outperforms baseline LVLMs across tasks like story generation and poetry composition. Our results demonstrate remarkable improvements, particularly in creativity and instruction adherence, validating VisuCraft's effectiveness in producing imaginative, visually grounded, and user-aligned long-form creative text. This work unlocks new potential for LVLMs in sophisticated creative AI applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 24 of its 32 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

24 of 32 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks9 Nov
  2. 2024VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization12 Feb
  3. 2023LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models15 Jun

Other references · 21

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  3. 2023Video-LLaVA: Learning United Visual Representation by Alignment Before Projectioncited by 1,402
  4. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
  5. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  6. 2024Visual In-Context Learning for Large Vision-Language Modelscited by 128
  7. 2024LMFusion: Adapting Pretrained Language Models for Multimodal Generationcited by 120
  8. 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 110
  9. 2023Prompting AI Art: An Investigation into the Creative Skill of Prompt Engineeringcited by 43
  10. 2024Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Modelscited by 42
  11. 2022Towards Robust Ranker for Text Retrievalcited by 37
  12. 2023KnowGPT: Knowledge Graph based Prompting for Large Language Modelscited by 31
9 more
  1. 2022Fine-Grained Distillation for Long Document Retrievalcited by 29
  2. 2024Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysiscited by 23
  3. 2023Improving Cross-modal Alignment for Text-Guided Image Inpaintingcited by 21
  4. 2024Prompt-Based Length Controlled Generation with Multiple Control Typescited by 19
  5. 2025Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocationcited by 16
  6. 2022SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learningcited by 8
  7. 2021COVID-19 Detection in Chest X-ray Images Using Swin-Transformer and Transformer in Transformercited by 6
  8. 2023STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Modelscited by 6
  9. 2024Multi-modal Generation via Cross-Modal In-Context Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025VLM-Guided Adaptive Negative Prompting for Creative Generation
  2. 2025Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM
  3. 2024GPTDrawer: Enhancing Visual Synthesis through ChatGPT
  4. 2023Learning to Imagine: Visually-Augmented Natural Language Generation
  5. 2026Can Language Models Imagine Without Seeing? Ekphrasis: Measuring Visual Creative Ideation in Text-Only LLMs
  6. 2025Mining Contextualized Visual Associations from Images for Creativity Understanding
  7. 2024GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation
  8. 2025Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation