LoRAverse: A Submodular Framework to Retrieve Diverse Adapters for Diffusion Models

2025-10-16 · Mert Sonmezer, Matthew Zheng, Pinar Yanardag arxiv

Low-rank Adaptation (LoRA) models have revolutionized the personalization of pre-trained diffusion models by enabling fine-tuning through low-rank, factorized weight matrices specifically optimized for attention layers. These models facilitate the generation of highly customized content across a variety of objects, individuals, and artistic styles without the need for extensive retraining. Despite the availability of over 100K LoRA adapters on platforms like Civit.ai, users often face challenges in navigating, selecting, and effectively utilizing the most suitable adapters due to their sheer volume, diversity, and lack of structured organization. This paper addresses the problem of selecting the most relevant and diverse LoRA models from this vast database by framing the task as a combinatorial optimization problem and proposing a novel submodular framework. Our quantitative and qualitative experiments demonstrate that our method generates diverse outputs across a wide range of domains.

📄 PDF Abstract BibTeX arXiv:2510.15022

Code (0)

등록된 구현이 없습니다.

Enhancing Multi-Image Question Answering via Submodular Subset Selection

2025-05-15 · Aaryan Sharma, Shivansh Gupta, Samar Agarwal, Vishak Prasad C. 외

Large multimodal models (LMMs) have achieved high performance in vision-language tasks involving single image but they struggle when presented with a collection of multiple images (Multiple Image Question Answering scena…

Question Answering Retrieval Visual Question Answering (VQA)

Parameter-Efficient Sparse Retrievers and Rerankers using Adapters

2023-03-23 · Vaishali Pal, Carlos Lassance, Hervé Déjean, Stéphane Clinchant

Parameter-Efficient transfer learning with Adapters have been studied in Natural Language Processing (NLP) as an alternative to full fine-tuning. Adapters are memory-efficient and scale well with downstream tasks by trai…

Domain Adaptation Information Retrieval Language Modelling Retrieval+1

Task-Aware LoRA Adapter Composition via Similarity Retrieval in Vector Databases

2026-02-01 · Riya Adsul, Balachandra Devarangadi Sunil, Isha Nalawade, Sudharshan Govindan arxiv

Parameter efficient fine tuning methods like LoRA have enabled task specific adaptation of large language models, but efficiently composing multiple specialized adapters for unseen tasks remains challenging. We present a…

Natural Language Inference Zero-shot Generalization Sentiment Analysis Question Answering

Signal from Structure: Exploiting Submodular Upper Bounds in Generative Flow Networks

2026-01-28 · Alexandre Larouche, Audrey Durand arxiv

Generative Flow Networks (GFlowNets; GFNs) are a class of generative models that learn to sample compositional objects proportionally to their a priori unknown value, their reward. We focus on the case where the reward h…

Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization

2016-06-22 · NeurIPS 2016 12 · Alexander Kirillov, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy

We consider the problem of jointly inferring the M-best diverse labelings for a binary (high-order) submodular energy of a graphical model. Recently, it was shown that this problem can be solved to a global optimum, for …

Diversity