EndoCoT:扩散模型中的内生思维链推理扩展
EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models
AI总结:
提出EndoCoT框架,通过迭代思维引导模块激活MLLM的推理潜力,并利用终端思维接地模块确保推理轨迹与文本监督对齐,使DiT逐步执行复杂任务,在多个基准上平均准确率达92.1%。
摘要:
最近,多模态大语言模型(MLLMs)被广泛集成到扩散框架中,主要作为文本编码器来处理空间推理等复杂任务。然而,这种范式存在两个关键限制:(i)MLLM文本编码器表现出不足的推理深度。单步编码无法激活思维链过程,而这对MLLM为复杂任务提供准确指导至关重要。(ii)在解码过程中,指导保持不变。即使有正确的MLLM编码,解码过程中的不变指导也阻止了DiT逐步将复杂指令分解为可执行的去噪步骤。为此,我们提出了内生思维链(EndoCoT),一种新颖的框架,首先通过迭代思维引导模块迭代细化潜在思维状态来激活MLLM的推理潜力,然后将这些状态桥接到DiT的去噪过程。其次,应用终端思维接地模块,通过将最终状态与真实答案对齐,确保推理轨迹保持与文本监督的接地。通过这两个组件,MLLM文本编码器提供精心推理的指导,使DiT能够逐步执行并最终以逐步方式解决复杂任务。在多个基准(如Maze、TSP、VSP和Sudoku)上的广泛评估实现了平均准确率92.1%,比最强基线高出8.3个百分点。代码和数据集在此https URL公开。
英文摘要:
Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such as spatial reasoning. However, this paradigm suffers from two critical limitations: (i) MLLMs text encoder exhibits insufficient reasoning depth. Single-step encoding fails to activate the Chain-of-Thought process, which is essential for MLLMs to provide accurate guidance for complex tasks. (ii) The guidance remains invariant during the decoding process. Invariant guidance during decoding prevents DiT from progressively decomposing complex instructions into actionable denoising steps, even with correct MLLM encodings. To this end, we propose Endogenous Chain-of-Thought (EndoCoT), a novel framework that first activates MLLMs' reasoning potential by iteratively refining latent thought states through an iterative thought guidance module, and then bridges these states to the DiT's denoising process. Second, a terminal thought grounding module is applied to ensure the reasoning trajectory remains grounded in textual supervision by aligning the final state with ground-truth answers. With these two components, the MLLM text encoder delivers meticulously reasoned guidance, enabling the DiT to execute it progressively and ultimately solve complex tasks in a step-by-step manner. Extensive evaluations across diverse benchmarks (e.g., Maze, TSP, VSP, and Sudoku) achieve an average accuracy of 92.1%, outperforming the strongest baseline by 8.3 percentage points. The code and dataset are publicly available at https://internlm.github.io/EndoCoT/.
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。