With the prevalence of pre-trained language models (PLMs) and the pre-training–fine-tuning
paradigm, it has been continuously shown that larger models tend to yield better …

Few-shot in-context learning (ICL) enables pre-trained language models to perform a
previously-unseen task without any gradient-based training by feeding a small number of …

Pre-trained vision-language models (eg, CLIP) have shown promising zero-shot
generalization in many downstream tasks with properly designed text prompts. Instead of …

Despite the success, the process of fine-tuning large-scale PLMs brings prohibitive
adaptation costs. In fact, fine-tuning all the parameters of a colossal model and retaining …

Prompt tuning provides an efficient way for users to customize Large Language Models
(LLMs) with their private data in the emerging LLM service scenario. However, the sensitive …

Self-supervised pre-training has drawn increasing attention in recent years due to its
superior performance on numerous downstream tasks after fine-tuning. However, it is well …

Recently, finetuning pretrained vision-language models (VLMs) has been a prevailing
paradigm for achieving state-of-the-art performance in VQA. However, as VLMs scale, it …

Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-
intensive multi-modal applications. However, existing methods face challenges in terms of …

Warning: this paper contains model outputs exhibiting offensiveness and biases. Recently
pre-trained language models (PLMs) have prospered in various natural language …

Abstract Out-of-distribution (OOD) detection, a fundamental task vexing real-world
applications, has attracted growing attention in the NLP community. Recently fine-tuning …