paper-with-me

Papers

DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models

2025-12-30 · Zefeng He, Xiaoye Qu, Yafu Li, Tong Zhu, Siyuan Huang, Yu Cheng arxiv

While recent Multimodal Large Language Models (MLLMs) have attained significant strides in multimodal reasoning, their reasoning processes remain predominantly text-centric, leading to suboptimal performance in complex long-horizon, vision-centric tasks. In this paper, we establish a novel Generative Multimodal Reasoning paradigm and introduce DiffThinker, a diffusion-based reasoning framework. Conceptually, DiffThinker reformulates multimodal reasoning as a native generative image-to-image task, achieving superior logical consistency and spatial precision in vision-centric tasks. We perform a systematic comparison between DiffThinker and MLLMs, providing the first in-depth investigation into the intrinsic characteristics of this paradigm, revealing four core properties: efficiency, controllability, native parallelism, and collaboration. Extensive experiments across four domains (sequential planning, combinatorial optimization, constraint satisfaction, and spatial configuration) demonstrate that DiffThinker significantly outperforms leading closed source models including GPT-5 (+314.2\%) and Gemini-3-Flash (+111.6\%), as well as the fine-tuned Qwen3-VL-32B baseline (+39.0\%), highlighting generative multimodal reasoning as a promising approach for vision-centric reasoning.

📄 PDF Abstract BibTeX arXiv:2512.24165

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal Reasoning

Similar Papers 제목 키워드 기반

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing

2025-09-30 · Yuxin Song, Wenkai Dong, Shizun Wang, Qi Zhang 외 arxiv

Unified Multimodal Models (UMMs) have demonstrated remarkable performance in text-to-image generation (T2I) and editing (TI2I), whether instantiated as assembled unified frameworks which couple powerful vision-language m…

Text-to-Image Generation

FairCoT: Enhancing Fairness in Diffusion Models via Chain of Thought Reasoning of Multimodal Language Models

2024-06-13 · Zahraa Al Sahili, Ioannis Patras, Matthew Purver

In the domain of text-to-image generative models, biases inherent in training datasets often propagate into generated content, posing significant ethical challenges, particularly in socially sensitive contexts. We introd…

AttributeDiversityFairness

DC3DO: Diffusion Classifier for 3D Objects

2024-08-13 · Nursena Koprucu, Meher Shashwat Nigam, Shicheng Xu, Biruk Abere 외

Inspired by Geoffrey Hinton emphasis on generative modeling, To recognize shapes, first learn to generate them, we explore the use of 3D diffusion models for object classification. Leveraging the density estimates from t…

3D Object ClassificationClassificationMultimodal ReasoningObject+2

Gen-VCoT: Generative Visual Chain-of-Thought Reasoning via Diffusion-Based RGB Intermediate Representations

2026-06-15 · Zhiqiang Zhou, Junliang Dai, Xu ling arxiv

Multimodal large language models (MLLMs) excel at visual reasoning but rely on text-based chain-of-thought (CoT), lacking interpretable visual intermediates. Existing methods use opaque tokens or external tools, missing …

Multimodal ReasoningVisual GroundingVisual Reasoning

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens

2025-04-20 · CVPR 2025 1 · Kaihang Pan, Wang Lin, Zhongqi Yue, Tenglong Ao 외

Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches re…

AttributeImage Generation