Related papers: Memory-Efficient Prompt Tuning for Incremental His…

Pre-trained protein models (PTPMs) represent a protein with one fixed embedding and thus are not capable for diverse tasks. For example, protein structures can shift, namely protein folding, between several conformations in various…

Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning. Using a large pre-trained language model (PLM), prefix-tuning can obtain strong performance by training…

Prompt-based continual learning provides a rehearsal-free solution by tuning small sets of parameters while keeping pre-trained models frozen. To meet the complex demands of sequential tasks, it is crucial to integrate task-specific…

Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity…

Generalist foundation models such as GPT-4 have displayed surprising capabilities in a wide variety of domains and tasks. Yet, there is a prevalent assumption that they cannot match specialist capabilities of fine-tuned models. For example,…

Parameter-efficient transfer learning (PETL) is proposed as a cost-effective way to transfer pre-trained models to downstream tasks, avoiding the high cost of updating entire large-scale pre-trained models (LPMs). In this work, we present…

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with…

Prompt tuning (PT) which only tunes the embeddings of an additional sequence of tokens per task, keeping the pre-trained language model (PLM) frozen, has shown remarkable performance in few-shot learning. Despite this, PT has been shown to…

Continual learning endeavors to equip the model with the capability to integrate current task knowledge while mitigating the forgetting of past task knowledge. Inspired by prompt tuning, prompt-based methods maintain a frozen backbone and…

Recently, prefix-tuning has gained increasing attention as a parameter-efficient finetuning method for large-scale pretrained language models. The method keeps the pretrained models fixed and only updates the prefix token parameters for…

Multi-rater medical image segmentation captures the inherent ambiguity of clinical interpretation, where diagnostic boundaries vary across experts and imaging devices. Existing approaches often reduce this diversity to consensus labels or…

Time series domain adaptation stands as a pivotal and intricate challenge with diverse applications, including but not limited to human activity recognition, sleep stage classification, and machine fault diagnosis. Despite the numerous…

Large pre-trained vision-language models have shown great prominence in transferring pre-acquired knowledge to various domains and downstream tasks with appropriate prompting or tuning. Existing prevalent tuning methods can be generally…

In this paper, we explore the task of mapping spoken language utterances to one of thousands of natural language understanding domains in intelligent personal digital assistants (IPDAs). This scenario is observed for many mainstream IPDAs…

Understanding human perceptions presents a formidable multimodal challenge for computers, encompassing aspects such as sentiment tendencies and sense of humor. While various methods have recently been introduced to extract…

In the evolving landscape of machine learning, the adaptation of pre-trained models through prompt tuning has become increasingly prominent. This trend is particularly observable in the graph domain, where diverse pre-training strategies…

Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits…

Histopathological images are essential for medical diagnosis and treatment planning, but interpreting them accurately using machine learning can be challenging due to variations in tissue preparation, staining and imaging protocols. Domain…

Foundational models such as the Segment Anything Model (SAM) are gaining traction in medical imaging segmentation, supporting multiple downstream tasks. However, such models are supervised in nature, still relying on large annotated…

Cross-modal hashing is a promising approach for efficient data retrieval and storage optimization. However, contemporary methods exhibit significant limitations in semantic preservation, contextual integrity, and information redundancy,…