Cover Image

Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained Experts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Esfandiari, Yasin, Bauer, Stefan, Stich, Sebastian U., Dittadi, Andrea
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

Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity
by: Li, Bo, et al.
Published: (2023)

Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models
by: Mamaghan, Amir Mohammad Karimi, et al.
Published: (2024)

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
by: Uselis, Arnas, et al.
Published: (2026)

DiffEnc: Variational Diffusion with a Learned Encoder
by: Nielsen, Beatrix M. G., et al.
Published: (2023)

Are Object-Centric Representations Better At Compositional Generalization?
by: Kapl, Ferdinand, et al.
Published: (2026)

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

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

Pretrained Diffusion Models Are Inherently Skipped-Step Samplers
by: Xu, Wenju
Published: (2025)

Efficient Multi-Source Knowledge Transfer by Model Merging
by: Osial, Marcin, et al.
Published: (2025)

Diffusion-Based Representation Learning
by: Mittal, Sarthak, et al.
Published: (2021)

MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
by: Qiu, Zihuan, et al.
Published: (2025)

Medical Semantic Segmentation with Diffusion Pretrain
by: Li, David, et al.
Published: (2025)

DC-Merge: Improving Model Merging with Directional Consistency
by: Zhang, Han-Chen, et al.
Published: (2026)

AdaMerging: Adaptive Model Merging for Multi-Task Learning
by: Yang, Enneng, et al.
Published: (2023)

EMR-Merging: Tuning-Free High-Performance Model Merging
by: Huang, Chenyu, et al.
Published: (2024)

Assessing Neural Network Robustness via Adversarial Pivotal Tuning
by: Christensen, Peter Ebert, et al.
Published: (2022)

Quantile-based Maximum Likelihood Training for Outlier Detection
by: Taghikhah, Masoud, et al.
Published: (2023)

CLIP with Quality Captions: A Strong Pretraining for Vision Tasks
by: Vasu, Pavan Kumar Anasosalu, et al.
Published: (2024)

Saliency-Aware Model Merging
by: Park, Jungin, et al.
Published: (2026)

Beyond Classification: Evaluating Diffusion Denoised Smoothing for Security-Utility Trade off
by: Belousov, Yury, et al.
Published: (2025)

Efficient Training of Diffusion Mixture-of-Experts Models: A Practical Recipe
by: Liu, Yahui, et al.
Published: (2025)

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics
by: Guo, Bowei, et al.
Published: (2025)

How to Merge Your Multimodal Models Over Time?
by: Dziadzio, Sebastian, et al.
Published: (2024)

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
by: Yang, Huitong, et al.
Published: (2025)

Boosting the Robustness-Accuracy Trade-off of SNNs by Robust Temporal Self-Ensemble
by: Wang, Jihang, et al.
Published: (2025)

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
by: Lu, Aojun, et al.
Published: (2025)

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
by: Zhang, Jiacheng, et al.
Published: (2024)

Benchmarking the Attribution Quality of Vision Models
by: Hesse, Robin, et al.
Published: (2024)

Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation
by: Chen, Tianyu, et al.
Published: (2025)

Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity
by: Joshi, Siddharth, et al.
Published: (2024)

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

Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations
by: Ding, Yifan, et al.
Published: (2025)

Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation
by: Zhao, Shiji, et al.
Published: (2023)

AgriPath: A Systematic Exploration of Architectural Trade-offs for Crop Disease Classification
by: Mooraj, Hamza, et al.
Published: (2026)

Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance
by: Kaur, Amandeep, et al.
Published: (2026)

Toward Early Quality Assessment of Text-to-Image Diffusion Models
by: Guo, Huanlei, et al.
Published: (2026)

Data Pruning in Generative Diffusion Models
by: Briq, Rania, et al.
Published: (2024)

Localizing Task Information for Improved Model Merging and Compression
by: Wang, Ke, et al.
Published: (2024)

CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones
by: Gong, Wenyi, et al.
Published: (2025)

MagMax: Leveraging Model Merging for Seamless Continual Learning
by: Marczak, Daniel, et al.
Published: (2024)