The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

Large models represent a groundbreaking advancement in multiple application fields,
enabling remarkable achievements across various tasks. However, their unprecedented …

We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA
into an instruction-following model. Using 52K self-instruct demonstrations, LLaMA-Adapter …

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 …

Large language models (LLMs) have demonstrated remarkable proficiency in
understanding and generating human-like texts, which may potentially revolutionize the …

To parameter-efficiently fine-tune (PEFT) large language models (LLMs), the low-rank
adaptation (LoRA) method approximates the model changes $\Delta W\in\mathbb …

Fine-tuning large pre-trained language models on downstream tasks has become an
important paradigm in NLP. However, common practice fine-tunes all of the parameters in a …

With the continuous growth in the number of parameters of transformer-based pretrained
language models (PLMs), particularly the emergence of large language models (LLMs) with …

Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …

Abstract Pretraining Vision Transformers (ViTs) has achieved great success in visual
recognition. A following scenario is to adapt a ViT to various image and video recognition …