Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yoon, Youngseok, Hu, Dainong, Weissburg, Iain, Qin, Yao, Jeong, Haewon
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition
by: Yoon, Youngseok, et al.
Published: (2024)

Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning
by: Ma, Qianli, et al.
Published: (2024)

Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion Models
by: Bao, Zhipeng, et al.
Published: (2023)

Finetuning Text-to-Image Diffusion Models for Fairness
by: Shen, Xudong, et al.
Published: (2023)

PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation
by: Hwang, Injoon, et al.
Published: (2024)

LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling
by: Jeon, Haewon, et al.
Published: (2026)

Controlling Text-to-Image Diffusion by Orthogonal Finetuning
by: Qiu, Zeju, et al.
Published: (2023)

Self-Correcting Self-Consuming Loops for Generative Model Training
by: Gillman, Nate, et al.
Published: (2024)

CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models
by: Cheng, Zihui, et al.
Published: (2024)

Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
by: Zang, Yuhang, et al.
Published: (2024)

Conditional Diffusion Model for Longitudinal Medical Image Generation
by: Dao, Duy-Phuong, et al.
Published: (2024)

Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models
by: Hong, Sujung, et al.
Published: (2026)

EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models
by: Lee, Eungbean, et al.
Published: (2024)

Position: AI/ML Influencers Have a Place in the Academic Process
by: Weissburg, Iain Xie, et al.
Published: (2024)

Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models
by: Fan, Jiawei, et al.
Published: (2026)

Nepotistically Trained Generative-AI Models Collapse
by: Bohacek, Matyas, et al.
Published: (2023)

Efficient Personalization of Quantized Diffusion Model without Backpropagation
by: Seo, Hoigi, et al.
Published: (2025)

DeepInv: A Novel Self-supervised Learning Approach for Fast and Accurate Diffusion Inversion
by: Zhang, Ziyue, et al.
Published: (2026)

Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images
by: Qiu, Tian, et al.
Published: (2025)

When Do Diffusion Models learn to Generate Multiple Objects?
by: Jeong, Yujin, et al.
Published: (2026)

Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspective
by: Shi, Yuguang
Published: (2024)

Quantitative Comparison of Fine-Tuning Techniques for Pretrained Latent Diffusion Models in the Generation of Unseen SAR Images
by: Debuysère, Solène, et al.
Published: (2025)

Robust Adverse Weather Removal via Spectral-based Spatial Grouping
by: Jeong, Yuhwan, et al.
Published: (2025)

APT: Improving Diffusion Models for High Resolution Image Generation with Adaptive Path Tracing
by: Han, Sangmin, et al.
Published: (2025)

DiffusionAgent: Navigating Expert Models for Agentic Image Generation
by: Qin, Jie, et al.
Published: (2024)

HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning
by: Hiranaka, Ayano, et al.
Published: (2024)

Improving Black-Box Generative Attacks via Generator Semantic Consistency
by: Jeong, Jongoh, et al.
Published: (2025)

Towards Better Ultrasound Video Segmentation Foundation Model: An Empirical study on SAM2 Finetuning from Data Perspective
by: Yao, Xing, et al.
Published: (2025)

A Novel Adaptive Fine-Tuning Algorithm for Multimodal Models: Self-Optimizing Classification and Selection of High-Quality Datasets in Remote Sensing
by: Ren, Yi, et al.
Published: (2024)

When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO
by: Zhang, Lingfan, et al.
Published: (2025)

Unmasking Bias in Diffusion Model Training
by: Yu, Hu, et al.
Published: (2023)

Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution
by: Bang, Junseo, et al.
Published: (2025)

Towards Self-Improvement of Diffusion Models via Group Preference Optimization
by: Chen, Renjie, et al.
Published: (2025)

Distilling Multi-view Diffusion Models into 3D Generators
by: Qin, Hao, et al.
Published: (2025)

High-quality Image Dehazing with Diffusion Model
by: Yu, Hu, et al.
Published: (2023)

Surgical Triplet Recognition via Diffusion Model
by: Liu, Daochang, et al.
Published: (2024)

Enabling Versatile Controls for Video Diffusion Models
by: Zhang, Xu, et al.
Published: (2025)

Mask Approximation Net: A Novel Diffusion Model Approach for Remote Sensing Change Captioning
by: Sun, Dongwei, et al.
Published: (2024)

Video Finetuning Improves Reasoning Between Frames
by: Yang, Ruiqi, et al.
Published: (2025)

A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse
by: Guo, Zhongliang, et al.
Published: (2024)