arXiv Machine Learning June 17, 2026 By Jisung Hwang, Yunhong Min, Jaihoon Kim, I-Chao Shen, Minhyuk Sung

NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment

Read the original on arXiv Machine Learning →

arXiv:2606. 18066v1 Announce Type: new Abstract: 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 sample per step.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 5

Latent Reward Registers for Diffusion Preference Alignment

arXiv:2608. 03929v1 Announce Type: new Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process.

By Yuanshen Guan, Zipeng Feng, Zhiwei Xiong, Peiqin Sun

llms diffusion reinforcement-learning efficiency benchmarks safety

arXiv Machine Learning

Jun 2

Gradient Preconditioning for Efficient and Reliable Reward-Guided Generation

arXiv:2602. 08646v3 Announce Type: replace Abstract: We propose a gradient preconditioning method that makes reward-guided generation with one-step generative models both efficient and reliable.

By Jisung Hwang, Minhyuk Sung

benchmarks

Hugging Face Trending Papers

Aug 7

Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models

Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences.

diffusion reinforcement-learning efficiency safety

arXiv AI

Jul 7

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models

arXiv:2603. 14504v2 Announce Type: replace-cross Abstract: Optimizing the noise samples of diffusion and flow models is an increasingly popular approach to align these models to target rewards at inference time.

By Niklas Schweiger, Daniel Cremers, Karnik Ram

diffusion safety

arXiv AI

Jun 2

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models

arXiv:2604. 17415v3 Announce Type: replace-cross Abstract: Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model.

By Jeongjae Lee, Jinho Chang, Jeongsol Kim, Jong Chul Ye

diffusion fine-tuning safety

arXiv AI

Jul 9

Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF

arXiv:2607. 07693v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models with human preferences.

By Eric Zhu, Abhinav Shrivastava, Soumik Mukhopadhyay

diffusion reinforcement-learning

Related stories

Latent Reward Registers for Diffusion Preference Alignment

Gradient Preconditioning for Efficient and Reliable Reward-Guided Generation

Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models

Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF