Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching
Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching
研究證明,在 Flow Matching 中加入自我條件化,可突破固定深度模型的表達能力瓶頸,令額外採樣步數轉化為更深層的視覺推理。受控實驗顯示,自我條件化 Flow Matching 在多種視覺推理任務中準確度更高、推理深度更大,且表現隨採樣步數增加而提升。理論上,加入自我條件化後,固定深度主幹模型可達到與空間有界圖靈機等同的表達能力。
Published on Oct 14
Authors:
,
,
,
,
,
Abstract
Flow matching with self-conditioning enables deeper visual reasoning by allowing iterative sampling steps to increase expressive power beyond constant-depth limits.
Recent work has explored visual reasoning through image generation, where models solve visual-reasoning problems by directly generating solution images. Intuitively, iterative samplers such as flow matching are well suited to this task, since each sampling step may resemble one reasoning step. However, in this work, from a circuit complexity perspective, we show that this intuition is misleading. We prove that as long as the model outputs satisfy certain mild regularity conditions, the trajectory of the vanilla flow-matching sampler can be simulated by a constant number of sequential rounds of parallel model evaluations. Consequently, additional sampling steps cannot increase the expressive power of a constant-depth backbone model under the standard complexity-theoretic model of transformers. We then reveal that self-conditioning, which conditions the model on the previous step's estimate of the final image, plays a previously unrecognized role in removing this bottleneck. Controlled experiments on diverse visual-reasoning tasks show that flow matching with self-conditioning achieves higher accuracy and greater reasoning depth than vanilla flow matching, and its performance improves with more sampling steps. Theoretically, we prove that with self-conditioning, a constant-depth backbone can achieve expressive power equivalent to that of space-bounded Turing machines. Our study suggests a design principle for future visual reasoning research: carry more information between sampling steps, so that additional steps translate into deeper reasoning.
View arXiv page View PDF GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.19628
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.19628 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.19628 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.19628 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co