噪声超网络：在扩散模型中分摊测试时计算成本

摘要

测试时缩放的新范式在大型语言模型（LLMs，如推理模型）和生成视觉模型中取得了显著突破，使得模型能够在推理过程中分配额外计算资源，以有效应对日益复杂的问题。尽管这种方法带来了改进，但一个重要限制也随之显现：计算时间的大幅增加使得该过程变得缓慢，在许多应用中显得不切实际。鉴于这一范式的成功及其日益广泛的应用，我们旨在保留其优势，同时避免推理开销。在本研究中，我们提出了一种解决方案，以解决在训练后阶段将测试时缩放知识整合到模型中的关键问题。具体而言，我们采用噪声超网络替代扩散模型中的奖励引导测试时噪声优化，该网络调节初始输入噪声。我们提出了一个理论基础的框架，通过一个可处理的噪声空间目标，为蒸馏生成器学习这种奖励倾斜的分布，在保持基础模型保真度的同时优化所需特性。我们展示了我们的方法以极低的计算成本，恢复了显式测试时优化带来的大部分质量提升。代码可在https://github.com/ExplainableML/HyperNoise获取。

English

The new paradigm of test-time scaling has yielded remarkable breakthroughs in Large Language Models (LLMs) (e.g. reasoning models) and in generative vision models, allowing models to allocate additional computation during inference to effectively tackle increasingly complex problems. Despite the improvements of this approach, an important limitation emerges: the substantial increase in computation time makes the process slow and impractical for many applications. Given the success of this paradigm and its growing usage, we seek to preserve its benefits while eschewing the inference overhead. In this work we propose one solution to the critical problem of integrating test-time scaling knowledge into a model during post-training. Specifically, we replace reward guided test-time noise optimization in diffusion models with a Noise Hypernetwork that modulates initial input noise. We propose a theoretically grounded framework for learning this reward-tilted distribution for distilled generators, through a tractable noise-space objective that maintains fidelity to the base model while optimizing for desired characteristics. We show that our approach recovers a substantial portion of the quality gains from explicit test-time optimization at a fraction of the computational cost. Code is available at https://github.com/ExplainableML/HyperNoise

噪声超网络：在扩散模型中分摊测试时计算成本

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

摘要

Support