paper-with-me

홈 › Papers

Diffusion Model Patching via Mixture-of-Prompts

2024-05-28 · Seokil Ham, Sangmin Woo, Jin-Young Kim, Hyojun Go, Byeongjun Park, Changick Kim

We present Diffusion Model Patching (DMP), a simple method to boost the performance of pre-trained diffusion models that have already reached convergence, with a negligible increase in parameters. DMP inserts a small, learnable set of prompts into the model's input space while keeping the original model frozen. The effectiveness of DMP is not merely due to the addition of parameters but stems from its dynamic gating mechanism, which selects and combines a subset of learnable prompts at every timestep (i.e., reverse denoising steps). This strategy, which we term "mixture-of-prompts", enables the model to draw on the distinct expertise of each prompt, essentially "patching" the model's functionality at every timestep with minimal yet specialized parameters. Uniquely, DMP enhances the model by further training on the original dataset already used for pre-training, even in a scenario where significant improvements are typically not expected due to model convergence. Notably, DMP significantly enhances the FID of converged DiT-L/2 by 10.38% on FFHQ, achieved with only a 1.43% parameter increase and 50K additional training iterations.

📄 PDF Abstract BibTeX arXiv:2405.17825

Code (0)

등록된 구현이 없습니다.

Tasks

Denoisingmodel

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Patching Activation patching studies the model's computation by altering its latent representations, the token embeddings in transformer-based language models, during the inference process
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Superscopes: Amplifying Internal Feature Representations for Language Model Interpretation

2025-03-03 · Jonathan Jacobi, Gal Niv

Understanding and interpreting the internal representations of large language models (LLMs) remains an open challenge. Patchscopes introduced a method for probing internal activations by patching them into new prompts, p…

Language ModelingLanguage Modelling

Improving Diffusion Model Efficiency Through Patching

2022-07-09 · Troy Luhman, Eric Luhman

Diffusion models are a powerful class of generative models that iteratively denoise samples to produce data. While many works have focused on the number of iterations in this sampling procedure, few have focused on the c…

model

Pathology Image Restoration via Mixture of Prompts

2025-03-16 · Jiangdong Cai, Yan Chen, Zhenrong Shen, Haotian Jiang 외

In digital pathology, acquiring all-in-focus images is essential to high-quality imaging and high-efficient clinical workflow. Traditional scanners achieve this by scanning at multiple focal planes of varying depths and …

Image Restoration

Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models

2026-05-29 · Shreyansh Modi, Akshat Tomar, Aarush Aggarwal arxiv

Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored. We show that h-space patching, the dominant paradigm for training-free …

Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers

2025-07-12 · Santhosh Kumar Ravindran

Large language models (LLMs) aligned for safety through techniques like reinforcement learning from human feedback (RLHF) often exhibit emergent deceptive behaviors, where outputs appear compliant but subtly mislead or o…

Anomaly Detection