Cover Image

Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Junyi, Luo, Weijian, Zheng, Haoyang, Zhang, Ruizhe, Lin, Guang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences
by: Luo, Weijian
Published: (2024)

David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training
by: Luo, Weijian, et al.
Published: (2024)

Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction
by: Wang, Yifei, et al.
Published: (2025)

Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation
by: Zheng, Bowen, et al.
Published: (2026)

Multi-student Diffusion Distillation for Better One-step Generators
by: Song, Yanke, et al.
Published: (2024)

One-Step Diffusion Distillation through Score Implicit Matching
by: Luo, Weijian, et al.
Published: (2024)

TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward
by: Luo, Yihong, et al.
Published: (2026)

Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models
by: Luo, Weijian, et al.
Published: (2023)

Di$\mathtt{[M]}$O: Distilling Masked Diffusion Models into One-step Generator
by: Zhu, Yuanzhi, et al.
Published: (2025)

One-step Diffusion Models with $f$-Divergence Distribution Matching
by: Xu, Yilun, et al.
Published: (2025)

One-step Diffusion Models with Bregman Density Ratio Matching
by: Zhu, Yuanzhi, et al.
Published: (2025)

RL for Consistency Models: Faster Reward Guided Text-to-Image Generation
by: Oertell, Owen, et al.
Published: (2024)

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
by: Lin, Zinan, et al.
Published: (2025)

Realism Control One-step Diffusion for Real-World Image Super-Resolution
by: Wu, Zongliang, et al.
Published: (2025)

FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning
by: Fu, Yuwei, et al.
Published: (2024)

ProxT2I: Efficient Reward-Guided Text-to-Image Generation via Proximal Diffusion
by: Fang, Zhenghan, et al.
Published: (2025)

Diffusion Adversarial Post-Training for One-Step Video Generation
by: Lin, Shanchuan, et al.
Published: (2025)

Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation
by: Luo, Yihong, et al.
Published: (2025)

Denoising Fisher Training For Neural Implicit Samplers
by: Luo, Weijian, et al.
Published: (2024)

DiffFinger: Advancing Synthetic Fingerprint Generation through Denoising Diffusion Probabilistic Models
by: Grabovski, Freddie, et al.
Published: (2024)

TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models
by: Ding, Zheng, et al.
Published: (2025)

One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
by: Bai, Zechen, et al.
Published: (2024)

Flow Generator Matching
by: Huang, Zemin, et al.
Published: (2024)

Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct
by: Zheng, Haoyang, et al.
Published: (2025)

MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing
by: Zhao, Haoyu, et al.
Published: (2023)

DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models
by: Chae, Daewon, et al.
Published: (2025)

DiffInject: Revisiting Debias via Synthetic Data Generation using Diffusion-based Style Injection
by: Ko, Donggeun, et al.
Published: (2024)

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
by: Zhou, Mingyuan, et al.
Published: (2024)

MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion
by: Wu, Lehong, et al.
Published: (2024)

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
by: Xu, Yilun, et al.
Published: (2024)

DiffBlender: Composable and Versatile Multimodal Text-to-Image Diffusion Models
by: Kim, Sungnyun, et al.
Published: (2023)

MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment
by: Liu, Jihao, et al.
Published: (2024)

DiffRaman: A Conditional Latent Denoising Diffusion Probabilistic Model for Bacterial Raman Spectroscopy Identification Under Limited Data Conditions
by: Yao, Haiming, et al.
Published: (2024)

AnimateDiff-Lightning: Cross-Model Diffusion Distillation
by: Lin, Shanchuan, et al.
Published: (2024)

STeP-Diff: Spatio-Temporal Physics-Informed Diffusion Models for Mobile Fine-Grained Pollution Forecasting
by: Zhou, Nan, et al.
Published: (2025)

Learning to Instruct for Visual Instruction Tuning
by: Zhou, Zhihan, et al.
Published: (2025)

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
by: Lee, Jeongjae, et al.
Published: (2026)

Hierarchical Variational Policies for Reward-Guided Diffusion
by: Pandey, Kushagra, et al.
Published: (2026)

Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation
by: Chen, Tianyu, et al.
Published: (2025)

When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On
by: Ikezogwo, Wisdom, et al.
Published: (2026)