思考像素：多模态扩散潜在中的递归稀疏推理
The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents
AI总结：
本文提出一种递归稀疏混合专家框架，用于提升多模态文本生成任务中视觉token的生成质量，通过递归机制和稀疏参数共享提高生成性能。
摘要：
扩散模型在高保真数据合成中取得成功，但其在复杂结构推理任务如文本跟随任务中的能力仍受限。尽管语言模型的进步利用了潜在推理和递归策略来增强文本理解能力，但将这些方法扩展到多模态文本到图像生成任务具有挑战性，因为视觉token是连续且非离散的。为此，我们受模块化人类认知启发，提出一种递归稀疏混合专家框架，整合到传统扩散模型中。我们的方法在联合注意力层中引入递归组件，通过多个潜在步骤迭代细化视觉token，同时通过稀疏选择神经模块高效共享参数。在每一步，设计了一个门控网络，根据当前视觉token、扩散时间步和条件信息动态选择专用神经模块。在类别条件ImageNet图像生成任务和GenEval和DPG基准的全面评估中，证明了所提方法在提升模型图像生成性能方面的优越性。
英文摘要：
Diffusion models have achieved success in high-fidelity data synthesis, yet their capacity for more complex, structured reasoning like text following tasks remains constrained. While advances in language models have leveraged strategies such as latent reasoning and recursion to enhance text understanding capabilities, extending these to multimodal text-to-image generation tasks is challenging due to the continuous and non-discrete nature of visual tokens. To tackle this problem, we draw inspiration from modular human cognition and propose a recursive, sparse mixture-of-experts framework integrated into conventional diffusion models. Our approach introduces a recursive component within joint attention layers that iteratively refines visual tokens over multiple latent steps while efficiently sharing parameters via sparse selection of neural modules. At each step, a gating network is devised to dynamically select specialized neural modules, conditioned on the current visual tokens, the diffusion timestep, and the conditioning information. Comprehensive evaluation on class-conditioned ImageNet image generation tasks and additional studies on the GenEval and DPG benchmark demonstrate the superiority of the proposed method in enhancing model image generation performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
