Cover Image

Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Ziyi, Zhang, Sen, Zhan, Yibing, Luo, Yong, Wen, Yonggang, Tao, Dacheng
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
by: Zhang, Ziyi, et al.
Published: (2024)

Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
by: Tang, Anke, et al.
Published: (2024)

Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases
by: Meo, Cristian, et al.
Published: (2024)

Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning
by: Hsu, Kyle, et al.
Published: (2024)

Image Captions are Natural Prompts for Text-to-Image Models
by: Lei, Shiye, et al.
Published: (2023)

Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models
by: Yang, Haobo, et al.
Published: (2025)

Diffusion Reward: Learning Rewards via Conditional Video Diffusion
by: Huang, Tao, et al.
Published: (2023)

Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
by: Teney, Damien, et al.
Published: (2025)

Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
by: Zhang, Ziyi, et al.
Published: (2025)

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
by: Shen, Li, et al.
Published: (2024)

Training Unbiased Diffusion Models From Biased Dataset
by: Kim, Yeongmin, et al.
Published: (2024)

LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization
by: Chen, Liang, et al.
Published: (2024)

On Inductive Biases That Enable Generalization of Diffusion Transformers
by: An, Jie, et al.
Published: (2024)

Diffusion Model-Based Video Editing: A Survey
by: Sun, Wenhao, et al.
Published: (2024)

IBiT: Utilizing Inductive Biases to Create a More Data Efficient Attention Mechanism
by: Giri, Adithya
Published: (2025)

Directly Fine-Tuning Diffusion Models on Differentiable Rewards
by: Clark, Kevin, et al.
Published: (2023)

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
by: Li, Quanhao, et al.
Published: (2026)

Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspective
by: Gui, Jie, et al.
Published: (2024)

Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
by: Hu, Zijing, et al.
Published: (2025)

UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
by: Wang, Jiaqi, et al.
Published: (2026)

$R_\text{dm}$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation
by: Fan, Linqian, et al.
Published: (2026)

Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL
by: Wu, Junyi, et al.
Published: (2026)

CDIMC-net: Cognitive Deep Incomplete Multi-view Clustering Network
by: Wen, Jie, et al.
Published: (2024)

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

Inductive Gradient Adjustment For Spectral Bias In Implicit Neural Representations
by: Shi, Kexuan, et al.
Published: (2024)

Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
by: Wang, Austin, et al.
Published: (2026)

GDRO: Group-level Reward Post-training Suitable for Diffusion Models
by: Wang, Yiyang, et al.
Published: (2026)

ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control
by: Golan, Shelly, et al.
Published: (2026)

Vision Language Models are Biased
by: Vo, An, et al.
Published: (2025)

A Geometric Perspective on Diffusion Models
by: Chen, Defang, et al.
Published: (2023)

TerDiT: Ternary Diffusion Models with Transformers
by: Lu, Xudong, et al.
Published: (2024)

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias
by: Jin, Haian, et al.
Published: (2024)

Reward-Forcing: Autoregressive Video Generation with Reward Feedback
by: Zhang, Jingran, et al.
Published: (2026)

Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models
by: Zhang, Xinxi, et al.
Published: (2024)

From Bias to Balance: Detecting Facial Expression Recognition Biases in Large Multimodal Foundation Models
by: Chhua, Kaylee, et al.
Published: (2024)

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

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

Unbiased Scene Graph Generation from Biased Training
by: Tang, Kaihua, et al.
Published: (2020)

Open-world machine learning: A review and new outlooks
by: Zhu, Fei, et al.
Published: (2024)

Reverse Prompt: Cracking the Recipe Inside Text-to-Image Generation
by: Ren, Zhiyao, et al.
Published: (2025)