paper-with-me

Papers

Gradient-Free Noise Optimization for Reward Alignment in Generative Models

2026-05-12 · Jeongsol Kim, Hongeun Kim, Jian Wang, Jong Chul Ye arxiv

Existing reward alignment methods for diffusion and flow models rely on multi-step stochastic trajectories, making them difficult to extend to deterministic generators. A natural alternative is noise-space optimization, but existing approaches require backpropagation through the generator and reward pipeline, limiting applicability to differentiable settings. To address this, here we present ZeNO (Zeroth-order Noise Optimization), a gradient-free framework that formulates noise optimization as a path-integral control problem, estimable from zeroth-order reward evaluations alone. When instantiated with an Ornstein--Uhlenbeck reference process, the update connects to Langevin dynamics implicitly targeting a reward-tilted distribution. ZeNO enables effective inference-time scaling and demonstrates strong performance across diverse generators and reward functions, including a protein structure generation task where backpropagation is infeasible.

📄 PDF Abstract BibTeX arXiv:2605.11347

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Inference-Time Alignment of Diffusion Models with Direct Noise Optimization

2024-05-29 · Zhiwei Tang, Jiangweizhi Peng, Jiasheng Tang, Mingyi Hong 외

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of…

Latent Reward Registers for Diffusion Preference Alignment

2026-08-04 · Yuanshen Guan, Zipeng Feng, Chengru Song, Zhiwei Xiong 외 arxiv

Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, which creates a severe temporal credit-assignment problem across the denoising process…

Reinforcement Learning

Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function

2025-12-04 · Hyeongyu Kang, Jaewoo Lee, Woocheol Shin, Kiyoung Om 외 arxiv

Diffusion models excel at generating high-likelihood samples but often require alignment with downstream objectives. Existing fine-tuning methods for diffusion models significantly suffer from reward over-optimization, r…

NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment

2026-06-16 · Jisung Hwang, Yunhong Min, Jaihoon Kim, I-Chao Shen 외 arxiv

We introduce the Noise-Tilted Reverse Kernel (NTRK), a reward-guided diffusion sampler that injects reward gradients through the noise term, leaving the pretrained reverse kernel unchanged and requiring only a single sam…

MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models

2025-10-02 · Kevin Zhai, Utsav Singh, Anirudh Thatipelli, Souradip Chakraborty 외 arxiv

Diffusion models excel at generating images conditioned on text prompts, but the resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aesthetic Scores. This alignment typically …