Related papers: SOP^2: Transfer Learning with Scene-Oriented Promp…

In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks. However, when extended to…

As the size of transformer-based models continues to grow, fine-tuning these large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. Parameter-efficient learning has been developed to reduce the…

Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks. However, prompt tuning requires a large training…

In real-world applications, the sample distribution at the inference stage often differs from the one at the training stage, causing performance degradation of trained deep models. The research on domain generalization (DG) aims to develop…

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to…

With the explosive 3D data growth, the urgency of utilizing zero-shot learning to facilitate data labeling becomes evident. Recently, methods transferring language or language-image pre-training models like Contrastive Language-Image…

This Monte Carlo simulation examines how prompt engineering strategies shape the quality of large language model (LLM)--generated personality assessment items within the AI-GENIE framework for generative psychometrics. Item pools targeting…

Automatic modulation classification (AMC) in real-world deployments demands robustness to distribution shifts arising from hardware impairments, unseen propagation environments, and recording conditions never encountered during training.…

Building models responsive to input prompts represents a transformative shift in machine learning. This paradigm holds significant potential for robotics problems, such as targeted manipulation amidst clutter. In this work, we present a…

This study introduces PEFT-DML, a parameter-efficient deep metric learning framework for robust multi-modal 3D object detection in autonomous driving. Unlike conventional models that assume fixed sensor availability, PEFT-DML maps diverse…

Prompt learning is a new paradigm in the Natural Language Processing (NLP) field which has shown impressive performance on a number of natural language tasks with common benchmarking text datasets in full, few-shot, and zero-shot…

State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of…

Soft prompt tuning techniques have recently gained traction as an effective strategy for the parameter-efficient tuning of pretrained language models, particularly minimizing the required adjustment of model parameters. Despite their…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models to downstream tasks. As large language models (LLMs) have emerged, recent studies have explored the use of category-related descriptions as input…

Current soft prompt methods yield limited performance when applied to small-sized models (fewer than a billion parameters). Deep prompt-tuning, which entails prepending parameters in each layer for enhanced efficacy, presents a solution for…

We investigate the generalization capabilities of small language models under two popular adaptation paradigms: few-shot prompting and supervised fine-tuning. While prompting is often favored for its parameter efficiency and flexibility, it…

Prompt engineering is still the primary way for users of generative text-to-image models to manipulate generated images in a targeted way. Based on treating the model as a continuous function and by passing gradients between the image space…

Visual prompt tuning (VPT) is a promising solution incorporating learnable prompt tokens to customize pre-trained models for downstream tasks. However, VPT and its variants often encounter challenges like prompt initialization, prompt…

Visual Prompt Tuning (VPT) has become a promising solution for Parameter-Efficient Fine-Tuning (PEFT) approach for Vision Transformer (ViT) models by partially fine-tuning learnable tokens while keeping most model parameters frozen. Recent…