Cover Image

Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Renye, Cheng, Jikang, Sun, Shikun, Sun, Yi, Wu, You, Peng, Wei, Wang, Zongwei, Liang, Ling, Xing, Junliang, Cai, Yimao
Format:	Preprint
Published:	2026
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

AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning
by: Yan, Renye, et al.
Published: (2024)

The Exploration-Exploitation Dilemma Revisited: An Entropy Perspective
by: Yan, Renye, et al.
Published: (2024)

Reflective Policy Optimization
by: Gan, Yaozhong, et al.
Published: (2024)

Doing More with Less.
by: Wagenveld, Linda M.
Published: (1987)

Doing Less for More: Consumer Search and Undertreatment in Credence Service Markets
by: Xu, Xiaoyan, et al.
Published: (2025)

Transductive Off-policy Proximal Policy Optimization
by: Gan, Yaozhong, et al.
Published: (2024)

We Need to Do This
by: Zabjek, Alexandra
Published: (2023)

Do We Need More Exercise and Osteoarthritis Randomized Clinical Trials?
by: Stephen P. Messier
Published: (2024)

Cognitive Tools for Understanding History: What More Do We Need?
by: O'neill, D. K., et al.
Published: (2006)

Diastolic Function in Acute Myocardial Infarction: Do We Need to Relax More?
by: Ioana Dregoesc, et al.
Published: (2025)

Fine-Grained Activation Steering: Steering Less, Achieving More
by: Feng, Zijian, et al.
Published: (2026)

Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture
by: Ma, Qichao, et al.
Published: (2024)

Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective
by: Jia, Zeyu, et al.
Published: (2025)

Do We Need Subsidiarity in Software?
by: Conwill, Louisa, et al.
Published: (2025)

Meeting the Challenges of the Information Age: Doing More with Less.
by: Gianini, Paul C., Jr.
Published: (1992)

Two-stage LLM Fine-tuning with Less Specialization and More Generalization
by: Wang, Yihan, et al.
Published: (2022)

Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models
by: Xiang, Bajian, et al.
Published: (2026)

Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning
by: Liao, Xinyao, et al.
Published: (2025)

When Generative Replay Meets Evolving Deepfakes: Domain-Aware Relative Weighting for Incremental Face Forgery Detection
by: Shen, Hao, et al.
Published: (2025)

Do We Still Need Controlled Vocabulary? Of Course, We Do! But How Do We Get It: The Roles for Text Analysis Softwares.
by: Greenfield, Rich
Published: (1997)

LIMR: Less is More for RL Scaling
by: Li, Xuefeng, et al.
Published: (2025)

Do We Really Even Need Data?
by: Hoffman, Kentaro, et al.
Published: (2024)

What Do We Need for an Agentic Society?
by: Ko, Kwon, et al.
Published: (2026)

Introduction: Why Do We Need Standards?
by: Hirsch, Felix E.
Published: (1972)

Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization
by: Chen, Yixiao, et al.
Published: (2025)

Doing More With Less: Mismatch-Based Risk-Limiting Audits
by: Ek, Alexander, et al.
Published: (2025)

Do We Really Need to Design New Byzantine-robust Aggregation Rules?
by: Fang, Minghong, et al.
Published: (2025)

A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real World
by: Cheng, Jikang, et al.
Published: (2025)

Make We Merry More and Less
by: Gray, Douglas
Published: (2019)

Doing More With Less: Towards More Data-Efficient Syndrome-Based Neural Decoders
by: Ismail, Ahmad, et al.
Published: (2025)

P‐1.11: Back‐End‐of‐Line Compatible Al‐doped Indium Zinc Oxide Transistors with Excellent Thermal Stability
by: Jingye Xie, et al.
Published: (2024)

Achieving More with Less: A Tensor-Optimization-Powered Ensemble Method
by: Yuan, Jinghui, et al.
Published: (2024)

Do We Need Tensor Cores for Stencil Computations?
by: Gu, Qiqi, et al.
Published: (2026)

When Do We Not Need Larger Vision Models?
by: Shi, Baifeng, et al.
Published: (2024)

Supernova: Achieving More with Less in Transformer Architectures
by: Tanase, Andrei-Valentin, et al.
Published: (2025)

Now That We Have Digital Collections, Why Do We Need Libraries?
by: Borgman, Christine L.
Published: (1997)

Code Less, Align More: Efficient LLM Fine-tuning for Code Generation with Data Pruning
by: Tsai, Yun-Da, et al.
Published: (2024)

Explain Less, Understand More: Jargon Detection via Personalized Parameter-Efficient Fine-tuning
by: Wu, Bohao, et al.
Published: (2025)

Do We Need to Design Specific Diffusion Models for Different Tasks? Try ONE-PIC
by: Tao, Ming, et al.
Published: (2024)

Do We Need All the Synthetic Data? Targeted Image Augmentation via Diffusion Models
by: Nguyen, Dang, et al.
Published: (2025)