It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Harrington, Anne, Koepke, A. Sophia, Karthik, Shyamgopal, Darrell, Trevor, Efros, Alexei A.
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
by: Koepke, A. Sophia, et al.
Published: (2026)

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
by: Eyring, Luca, et al.
Published: (2025)

Simplifying Knowledge Transfer in Pretrained Models
by: Jain, Siddharth, et al.
Published: (2025)

ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
by: Eyring, Luca, et al.
Published: (2024)

Vision-by-Language for Training-Free Compositional Image Retrieval
by: Karthik, Shyamgopal, et al.
Published: (2023)

Test-Time Training on Video Streams
by: Wang, Renhao, et al.
Published: (2023)

Interpreting the Weight Space of Customized Diffusion Models
by: Dravid, Amil, et al.
Published: (2024)

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
by: Pach, Mateusz, et al.
Published: (2025)

Fast Data Attribution for Text-to-Image Models
by: Wang, Sheng-Yu, et al.
Published: (2025)

Data Attribution for Text-to-Image Models by Unlearning Synthesized Images
by: Wang, Sheng-Yu, et al.
Published: (2024)

Disentangled 3D Scene Generation with Layout Learning
by: Epstein, Dave, et al.
Published: (2024)

Solving Spatial Supersensing Without Spatial Supersensing
by: Udandarao, Vishaal, et al.
Published: (2025)

Diffusion Models as Data Mining Tools
by: Siglidis, Ioannis, et al.
Published: (2024)

Rethinking Patch Dependence for Masked Autoencoders
by: Fu, Letian, et al.
Published: (2024)

Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting
by: Bhattad, Anand, et al.
Published: (2025)

Interpreting the Second-Order Effects of Neurons in CLIP
by: Gandelsman, Yossi, et al.
Published: (2024)

Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models
by: Kurzendörfer, David, et al.
Published: (2024)

Post-hoc Probabilistic Vision-Language Models
by: Baumann, Anton, et al.
Published: (2024)

Vision Transformers Don't Need Trained Registers
by: Jiang, Nick, et al.
Published: (2025)

Vision-Language Models Create Cross-Modal Task Representations
by: Luo, Grace, et al.
Published: (2024)

IT$^3$: Idempotent Test-Time Training
by: Durasov, Nikita, et al.
Published: (2024)

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models
by: Lian, Long, et al.
Published: (2023)

Segment Anything without Supervision
by: Wang, XuDong, et al.
Published: (2024)

Scalable Ranked Preference Optimization for Text-to-Image Generation
by: Karthik, Shyamgopal, et al.
Published: (2024)

Concept-Guided Interpretability via Neural Chunking
by: Wu, Shuchen, et al.
Published: (2025)

Interpreting CLIP's Image Representation via Text-Based Decomposition
by: Gandelsman, Yossi, et al.
Published: (2023)

Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model
by: Roth, Karsten, et al.
Published: (2023)

The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio
by: Wang, Renhao, et al.
Published: (2025)

Continuous 3D Perception Model with Persistent State
by: Wang, Qianqian, et al.
Published: (2025)

EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval
by: Hummel, Thomas, et al.
Published: (2024)

NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
by: Wu, Fang, et al.
Published: (2026)

InstanceDiffusion: Instance-level Control for Image Generation
by: Wang, Xudong, et al.
Published: (2024)

On the Dangers of Bootstrapping Generation for Continual Learning and Beyond
by: Zverev, Daniil, et al.
Published: (2025)

Personalizing Text-to-Image Generation to Individual Taste
by: Maerten, Anne-Sofie, et al.
Published: (2026)

Reconstruction Alignment Improves Unified Multimodal Models
by: Xie, Ji, et al.
Published: (2025)

Coordinated Sparse Recovery of Label Noise
by: Yang, Yukun, et al.
Published: (2024)

Neural Network Diffusion
by: Wang, Kai, et al.
Published: (2024)

UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
by: Yu, Junwei, et al.
Published: (2025)

Diffusion Models With Learned Adaptive Noise
by: Sahoo, Subham Sekhar, et al.
Published: (2023)

Sparse-to-Sparse Training of Diffusion Models
by: Oliveira, Inês Cardoso, et al.
Published: (2025)