Cover Image

Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liao, Xinyao, Wei, Wei, Qu, Xiaoye, Cheng, Yu
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
by: Yan, Renye, et al.
Published: (2026)

VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation
by: Liao, Xinyao, et al.
Published: (2026)

Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning
by: Qu, Xiaoye, et al.
Published: (2024)

SATORI-R1: Incentivizing Multimodal Reasoning through Explicit Visual Anchoring
by: Shen, Chuming, et al.
Published: (2025)

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

Mitigating Multilingual Hallucination in Large Vision-Language Models
by: Qu, Xiaoye, et al.
Published: (2024)

DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models
by: He, Zefeng, et al.
Published: (2025)

DRM: Diffusion-based Reward Model With Step-wise Guidance
by: Zhang, Jaxon, et al.
Published: (2026)

A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends
by: Liu, Daizong, et al.
Published: (2024)

VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL
by: Dai, Fengyuan, et al.
Published: (2025)

Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning
by: Wang, Yifan, et al.
Published: (2026)

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

Efficient Vision Language Model Fine-tuning for Text-based Person Anomaly Search
by: He, Jiayi, et al.
Published: (2025)

DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Driving
by: Tu, Jiahang, et al.
Published: (2024)

DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models
by: Marjit, Shyam, et al.
Published: (2024)

Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints
by: Chen, Guanjie, et al.
Published: (2024)

Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution
by: Tai, Yu-Shan, et al.
Published: (2026)

Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening
by: Tian, Ye, et al.
Published: (2025)

Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
by: Li, Mingxiao, et al.
Published: (2023)

Coffee: Controllable Diffusion Fine-tuning
by: Zeng, Ziyao, et al.
Published: (2025)

Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
by: Chen, Honghao, et al.
Published: (2025)

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
by: Yang, Kai, et al.
Published: (2023)

Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization
by: Zhang, Tao, et al.
Published: (2025)

VA-$π$: Variational Policy Alignment for Pixel-Aware Autoregressive Generation
by: Liao, Xinyao, et al.
Published: (2025)

From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration
by: Song, Mingyang, et al.
Published: (2025)

MARBLE: Multi-Aspect Reward Balance for Diffusion RL
by: Zhao, Canyu, et al.
Published: (2026)

RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
by: Tang, Yinzhou, et al.
Published: (2025)

MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent
by: Liao, Xinyao, et al.
Published: (2025)

Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think
by: Tian, Jie, et al.
Published: (2025)

Personalized Preference Fine-tuning of Diffusion Models
by: Dang, Meihua, et al.
Published: (2025)

StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Models
by: Tang, Qiuyu, et al.
Published: (2025)

FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Models
by: Zhou, Hongyu, et al.
Published: (2026)

OSDM-MReg: Multimodal Image Registration based One Step Diffusion Model
by: Wei, Xiaochen, et al.
Published: (2025)

Fine-tuning Pre-trained Vision-Language Models in a Human-Annotation-Free Manner
by: Wang, Qian-Wei, et al.
Published: (2026)

SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information
by: Sun, Jiashuo, et al.
Published: (2024)

Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation
by: Qu, Xiaoye, et al.
Published: (2024)

FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution
by: Liu, Yidi, et al.
Published: (2025)

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
by: Zhou, Ziqi, et al.
Published: (2024)

FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion Models
by: Chen, Changgu, et al.
Published: (2024)

CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL
by: Ni, Zhenyang, et al.
Published: (2026)