paper-with-me

홈 › Papers

AdvDMD: Adversarial Reward Meets DMD For High-Quality Few-Step Generation

2026-04-29 · Xu Wang, Zexian Li, Litong Gong, Tiezheng Ge, Zhijie Deng arxiv

Diffusion models offer superior generation quality at the expense of extensive sampling steps. Distillation methods, with Distribution Matching Distillation (DMD) as a popular example, can mitigate this issue, but performance degradation remains pronounced when sampling steps are limited. Reinforcement learning (RL) has been leveraged to improve the few-step generation quality during distillation, with the potential to even surpass the performance of the teacher model. However, existing approaches are combinatorial in nature, merely integrating an RL process with the distillation process, which introduces unnecessary complexities. To address this gap, we propose AdvDMD, a method that seamlessly unifies DMD distillation and RL. Specifically, AdvDMD employs the adversarially trained discriminator from DMD2 as the reward model, which assigns low scores to generated images and high scores to real ones. It is trained on both intermediate and final states of the denoising process and updated online with the distilled model, enabling a holistic supervision of the sampling trajectories and mitigating reward hacking. We adopt a unified SDE backward simulation and a different training schedule for DMD and RL to enable a more stable and efficient training. Experimental results demonstrate that the 4-step AdvDMD outperforms the original 40-step model for SD3.5 on DPG-Bench, while achieving significant performance gains for SD3 on the GenEval. On Qwen-Image, our 2-step AdvDMD achieves superior performance over TwinFlow.

📄 PDF Abstract BibTeX arXiv:2604.28126

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

When Molecular GAN Meets Byte-Pair Encoding

2024-09-29 · Huidong Tang, Chen Li, Yasuhiko Morimoto

Deep generative models, such as generative adversarial networks (GANs), are pivotal in discovering novel drug-like candidates via de novo molecular generation. However, traditional character-wise tokenizers often struggl…

Computational EfficiencyDiversity

Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning

2018-12-09 · Ziming Li, Julia Kiseleva, Maarten de Rijke

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may l…

Dialogue GenerationImitation Learningreinforcement-learningReinforcement Learning+1

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation

2025-11-25 · Weijia Mao, Hao Chen, Zhenheng Yang, Mike Zheng Shou arxiv

A reliable reward function is essential for reinforcement learning (RL) in image generation. Most current RL approaches depend on pre-trained preference models that output scalar rewards to approximate human preferences.…

Reinforcement LearningImage Generation

EBaReT: Expert-guided Bag Reward Transformer for Auto Bidding

2025-07-22 · Kaiyuan Li, Pengyu Wang, Yunshan Peng, Pengjia Yuan 외 arxiv

Reinforcement learning has been widely applied in automated bidding. Traditional approaches model bidding as a Markov Decision Process (MDP). Recently, some studies have explored using generative reinforcement learning m…

Reinforcement Learning

Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks

2022-12-28 · Junlin Wu, Hussein Sibai, Yevgeniy Vorobeychik

Function approximation has enabled remarkable advances in applying reinforcement learning (RL) techniques in environments with high-dimensional inputs, such as images, in an end-to-end fashion, mapping such inputs direct…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)