Unified Thinker: A General Reasoning Modular Core for Image Generation
- URL: http://arxiv.org/abs/2601.03127v1
- Date: Tue, 06 Jan 2026 15:59:33 GMT
- Title: Unified Thinker: A General Reasoning Modular Core for Image Generation
- Authors: Sashuai Zhou, Qiang Zhou, Jijin Hu, Hanqing Yang, Yue Cao, Junpeng Ma, Yinchao Ma, Jun Song, Tiezheng Ge, Cheng Yu, Bo Zheng, Zhou Zhao,
- Abstract summary: We propose Unified Thinker, a task-agnostic reasoning architecture for general image generation.<n>Unified Thinker decouples a dedicated Thinker from the image Generator, enabling modular upgrades of reasoning without retraining the entire generative model.<n>Experiments on text-to-image generation and image editing show that Unified Thinker substantially improves image reasoning and generation quality.
- Score: 57.665309753609144
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Despite impressive progress in high-fidelity image synthesis, generative models still struggle with logic-intensive instruction following, exposing a persistent reasoning--execution gap. Meanwhile, closed-source systems (e.g., Nano Banana) have demonstrated strong reasoning-driven image generation, highlighting a substantial gap to current open-source models. We argue that closing this gap requires not merely better visual generators, but executable reasoning: decomposing high-level intents into grounded, verifiable plans that directly steer the generative process. To this end, we propose Unified Thinker, a task-agnostic reasoning architecture for general image generation, designed as a unified planning core that can plug into diverse generators and workflows. Unified Thinker decouples a dedicated Thinker from the image Generator, enabling modular upgrades of reasoning without retraining the entire generative model. We further introduce a two-stage training paradigm: we first build a structured planning interface for the Thinker, then apply reinforcement learning to ground its policy in pixel-level feedback, encouraging plans that optimize visual correctness over textual plausibility. Extensive experiments on text-to-image generation and image editing show that Unified Thinker substantially improves image reasoning and generation quality.
Related papers
- RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection [18.52946282633359]
RL-RIG is a Reinforcement Learning framework for Reflection-based Image Generation.<n>We develop Reflection-GRPO to train the VLM Actor for edit prompts and the Image Editor for better image quality under a given prompt.<n> Experimental results show that RL-RIG outperforms existing state-of-the-art open-source models by up to 11% in terms of controllable and precise spatial reasoning in image generation.
arXiv Detail & Related papers (2026-02-23T15:39:53Z) - Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation [47.97278965762397]
We introduce Mind-Brush, a unified agentic framework that transforms generation into a dynamic, knowledge-driven workflow.<n>Simulating a human-like 'think-research-create' paradigm, Mind-Brush actively retrieves multimodal evidence to ground out-of-distribution concepts.<n>Extensive experiments demonstrate that Mind-Brush significantly enhances the capabilities of unified models.
arXiv Detail & Related papers (2026-02-02T07:42:13Z) - HiCoGen: Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement Learning [66.99487505369254]
HiCoGen is built upon a novel Chain of Synthesis paradigm.<n>It decomposes complex prompts into minimal semantic units.<n>It then synthesizes these units iteratively, where the image generated in each step provides crucial visual context for the next.<n>Experiments show our approach significantly outperforms existing methods in both concept coverage and compositional accuracy.
arXiv Detail & Related papers (2025-11-25T06:24:25Z) - ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection [51.93101033997245]
Increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations.<n>We propose ThinkFake, a novel reasoning-based and generalizable framework for AI-generated image detection.<n>We show that ThinkFake outperforms state-of-the-art methods on the GenImage benchmark and demonstrates strong zero-shot generalization on the challenging LOKI benchmark.
arXiv Detail & Related papers (2025-09-24T07:34:09Z) - Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation [43.98469957837991]
We propose a novel reasoning framework for unified models, Understanding-in-Generation (UiG)<n>The core insight of our UiG is to integrate generative guidance by the strong understanding capabilities during the reasoning process.<n>Our UiG framework demonstrates a significant performance improvement in text-to-image generation over existing text-to-image reasoning methods.
arXiv Detail & Related papers (2025-09-23T04:52:39Z) - Interleaving Reasoning for Better Text-to-Image Generation [83.69082794730664]
We introduce Interleaving Reasoning Generation (IRG), a framework that alternates between text-based thinking and image synthesis.<n>To train IRG effectively, we propose Interleaving Reasoning Generation Learning (IRGL), which targets two sub-goals.<n>Experiments show SoTA performance, yielding absolute gains of 5-10 points on GenEval, WISE, TIIF, GenAI-Bench, and OneIG-EN.
arXiv Detail & Related papers (2025-09-08T17:56:23Z) - ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL [54.100889131719626]
Chain-of-thought reasoning and reinforcement learning have driven breakthroughs in NLP.<n>We introduce ReasonGen-R1, a framework that imbues an autoregressive image generator with explicit text-based "thinking" skills.<n>We show that ReasonGen-R1 consistently outperforms strong baselines and prior state-of-the-art models.
arXiv Detail & Related papers (2025-05-30T17:59:48Z) - Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model [118.52589065972795]
We introduce Muddit, a unified discrete diffusion transformer that enables fast and parallel generation across both text and image modalities.<n>Unlike prior unified diffusion models trained from scratch, Muddit integrates strong visual priors from a pretrained text-to-image backbone with a lightweight text decoder.
arXiv Detail & Related papers (2025-05-29T16:15:48Z) - Thinking with Generated Images [30.28526622443551]
We present Thinking with Generated Images, a novel paradigm that transforms how large multimodal models (LMMs) engage with visual reasoning.<n>Our approach enables AI models to engage in the kind of visual imagination and iterative refinement that characterizes human creative, analytical, and strategic thinking.
arXiv Detail & Related papers (2025-05-28T16:12:45Z) - Autoregressive Image Generation with Vision Full-view Prompt [18.569610688433745]
We propose Vision Full-view prompt (VF prompt) to enhance autoregressive image generation.<n>Inspired by prompt engineering from the field of NLP, we propose Vision Full-view prompt (VF prompt) to enhance autoregressive image generation.
arXiv Detail & Related papers (2025-02-24T08:44:01Z)
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.