Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation
Jun He, Junyan Ye, Zilong Huang, Dongzhi Jiang, Chenjue Zhang, Leqi Zhu, Renrui Zhang, Xiang Zhang, Weijia Li

TL;DR
Mind-Brush introduces an agentic, knowledge-driven framework for image generation that actively retrieves evidence and employs reasoning, significantly improving understanding and task performance over static models.
Contribution
It presents a novel unified framework that integrates active knowledge retrieval and reasoning into image generation, enabling dynamic, context-aware outputs.
Findings
Significantly improves performance on Mind-Bench benchmark.
Achieves a zero-to-one capability leap over baseline models.
Outperforms existing models on WISE and RISE benchmarks.
Abstract
While text-to-image generation has achieved unprecedented fidelity, the vast majority of existing models function fundamentally as static text-to-pixel decoders. Consequently, they often fail to grasp implicit user intentions. Although emerging unified understanding-generation models have improved intent comprehension, they still struggle to accomplish tasks involving complex knowledge reasoning within a single model. Moreover, constrained by static internal priors, these models remain unable to adapt to the evolving dynamics of the real world. To bridge these gaps, we introduce Mind-Brush, a unified agentic framework that transforms generation into a dynamic, knowledge-driven workflow. Simulating a human-like 'think-research-create' paradigm, Mind-Brush actively retrieves multimodal evidence to ground out-of-distribution concepts and employs reasoning tools to resolve implicit visual…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Generative Adversarial Networks and Image Synthesis · Data Visualization and Analytics
