Related papers: Meta-LoRA: Meta-Learning LoRA Components for Domai…

Low-rank Adaptation (LoRA) has gained popularity as a fine-tuning approach for Large Language Models (LLMs) due to its low resource requirements and good performance. While a plethora of work has investigated improving LoRA serving…

This paper introduces Bayesian Hierarchical Low-Rank Adaption (BoRA), a novel method for finetuning multi-task Large Language Models (LLMs). Current finetuning approaches, such as Low-Rank Adaption (LoRA), perform exeptionally well in…

Reliable detection of speech deepfakes (spoofs) must remain effective when the distribution of spoofing attacks shifts. We frame the task as domain generalization and show that inserting Low-Rank Adaptation (LoRA) adapters into every…

Low-rank adaptations (LoRAs) have revolutionized the finetuning of large foundation models, enabling efficient adaptation even with limited computational resources. The resulting proliferation of LoRAs presents exciting opportunities for…

Existing video personalization methods preserve visual likeness but treat video and audio separately. Without access to the visual scene, audio models cannot synchronize sounds with on-screen actions; and because classical voice-cloning…

Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras. A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a…

In the past, continual learning (CL) was mostly concerned with the problem of catastrophic forgetting in neural networks, that arises when incrementally learning a sequence of tasks. Current CL methods function within the confines of…

Learning-based image dehazing methods are essential to assist autonomous systems in enhancing reliability. Due to the domain gap between synthetic and real domains, the internal information learned from synthesized images is usually…

Low-Rank Adaptation (LoRA) enables efficient fine-tuning of pre-trained language models through low-rank matrix approximation, achieving effectiveness in many scenarios. However, its representation capacity is constrained in complex tasks…

We focus on bridging domain discrepancy in lane detection among different scenarios to greatly reduce extra annotation and re-training costs for autonomous driving. Critical factors hinder the performance improvement of cross-domain lane…

We primarily focus on the field of large language models (LLMs) for recommendation, which has been actively explored recently and poses a significant challenge in effectively enhancing recommender systems with logical reasoning abilities…

Object detectors trained on large-scale RGB datasets are being extensively employed in real-world applications. However, these RGB-trained models suffer a performance drop under adverse illumination and lighting conditions. Infrared (IR)…

Recent advancements in training paradigms for Large Language Models (LLMs) have unlocked their remarkable capabilities in natural language processing and cross-domain generalization. While LLMs excel in tasks like programming and…

Low-Rank Adaptation (LoRA) emerges as a popular parameter-efficient fine-tuning (PEFT) method, which proposes to freeze pretrained model weights and update an additive low-rank trainable matrix. In this work, we study the enhancement of…

Prompt-based all-in-one image restoration (IR) frameworks have achieved remarkable performance by incorporating degradation-specific information into prompt modules. Nevertheless, handling the complex and diverse degradations encountered in…

Fine-tuning is widely used to tailor large language models for specific tasks such as neural machine translation (NMT). However, leveraging transfer learning is computationally expensive when fine-tuning large multilingual models with…

The rapid evolution of Large Language Models (LLMs) has shifted focus from general-purpose capabilities to domain-specific expertise. However, adapting LLMs to specialized fields such as medicine presents two challenge: (1) the…

Low-Rank Adaptation (LoRA) is the prevailing approach for efficient large language model (LLM) fine-tuning. Building on this paradigm, recent studies have proposed alternative initialization strategies, architectural modifications, and…

The deployment of large language models for specialized tasks often requires domain-specific parameter-efficient finetuning through Low-Rank Adaptation (LoRA) modules. However, effectively fusing these adapters to handle complex,…

In recent years, Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA) have significantly enhanced the adaptability of large-scale pre-trained models. Weight-Decomposed Low-Rank Adaptation (DoRA) improves upon LoRA…