多步视觉推理中的层级去噪

摘要

视频模型正在向视觉基础模型演进，但仍缺乏类人的多步推理能力。流式自回归扩散模型虽高效，但推理能力有限；而双向扩散虽能实现全局修正，却因密集帧级去噪导致推理成本高昂。这两种范式均难以在复杂推理任务中兼顾逻辑一致性与低延迟流式输出。我们提出HDR（层次化视觉推理去噪），一种将层次化潜在变量融入因果视频生成的统一框架，用于多步推理。HDR将视频潜在变量组织为树状层次结构，支持在流式输出前进行由粗到细的推理。粗去噪层保留不确定假设以进行全局规划，细层则逐步将其精化为具体视觉状态。稀疏层次化注意力模式（SHAP）进一步降低了时序注意力成本。我们引入了一个包含分布外案例的分层多步视频推理基准，涵盖迷宫导航、汉诺塔、一笔画、滑动拼图、推箱子和倒水六类任务。与流式自回归扩散基线相比，HDR将成功率从34.22提升至60.29（相对增益76.2%），平均进度从76.00提升至89.56，展现出更一致的推理轨迹。HDR以每个潜在变量0.70秒保持低延迟流式输出，推理速度比双向扩散快54.2倍。在仅使用2%训练数据时，HDR仍能保留全数据性能的82.9%，而双向扩散仅保留52.0%。真实机器人实验进一步证明了HDR在物理交互与世界建模中的潜力。项目演示：https://hierarchical-diffusion-reasoning.github.io/。

English

Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusion enables global revision with high inference costs due to dense frame-level denoising. Both paradigms struggle to achieve logical consistency and low-latency streaming for complex reasoning tasks. We propose HDR (Hierarchical Denoising for Visual Reasoning), a unified framework that integrates hierarchical latents into causal video generation for multi-step reasoning. HDR organizes video latents into a tree-structured hierarchy, enabling coarse-to-fine reasoning before streaming output. Coarse denoising layers preserve uncertain hypotheses for global planning, while finer layers progressively refine them into concrete visual states. A sparse hierarchical attention pattern (SHAP) further reduces temporal attention costs. We introduce a level-stratified multi-step video reasoning benchmark with out-of-distribution cases, covering six tasks: maze navigation, Tower of Hanoi, one-line drawing, sliding puzzle, Sokoban, and water pouring. Compared with streaming autoregressive diffusion baselines, HDR improves success from 34.22 to 60.29 (76.2% relative gain) and increases average progress from 76.00 to 89.56, demonstrating more consistent reasoning trajectories. HDR maintains low-latency streaming at 0.70 seconds per latent, achieving 54.2 times faster inference than bidirectional diffusion. It also retains 82.9% of full-data performance with only 2% training data, compared with 52.0% for bidirectional diffusion. Real-world robot experiments further demonstrate HDR's potential for physical interaction and world modeling. Project demo: https://hierarchical-diffusion-reasoning.github.io/.