Adapter is all you need for tuning visual tasks
D Yin, L Hu, B Li, Y Zhang - arXiv preprint arXiv:2311.15010, 2023 - arxiv.org
Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual
tasks. Recent delta-tuning methods provide more options for visual classification tasks …
tasks. Recent delta-tuning methods provide more options for visual classification tasks …
BiGRU-ANN based hybrid architecture for intensified classification tasks with explainable AI
S Chakraborty, MBU Talukder, MM Hasan… - International Journal of …, 2023 - Springer
Artificial Intelligence (AI) is increasingly being employed in critical decision-making
processes such as medical diagnosis, credit approval, criminal justice, and many more …
processes such as medical diagnosis, credit approval, criminal justice, and many more …
One model for all domains: collaborative domain-prefix tuning for cross-domain NER
Cross-domain NER is a challenging task to address the low-resource problem in practical
scenarios. Previous typical solutions mainly obtain a NER model by pre-trained language …
scenarios. Previous typical solutions mainly obtain a NER model by pre-trained language …
Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models
The high cost of full-parameter fine-tuning (FFT) of Large Language Models (LLMs) has led
to a series of parameter-efficient fine-tuning (PEFT) methods. However, it remains unclear …
to a series of parameter-efficient fine-tuning (PEFT) methods. However, it remains unclear …
5%> 100%: Breaking performance shackles of full fine-tuning on visual recognition tasks
Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual
tasks. Recent delta-tuning methods provide more options for visual classification tasks …
tasks. Recent delta-tuning methods provide more options for visual classification tasks …
Pvp: Pre-trained visual parameter-efficient tuning
Z Song, K Yang, N Guan, J Zhu, P Qiao… - arXiv preprint arXiv …, 2023 - arxiv.org
Large-scale pre-trained transformers have demonstrated remarkable success in various
computer vision tasks. However, it is still highly challenging to fully fine-tune these models …
computer vision tasks. However, it is still highly challenging to fully fine-tune these models …
Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks
Real-world natural language processing systems need to be robust to human adversaries.
Collecting examples of human adversaries for training is an effective but expensive solution …
Collecting examples of human adversaries for training is an effective but expensive solution …
Jointly reparametrized multi-layer adaptation for efficient and private tuning
Efficient finetuning of pretrained language transformers is becoming increasingly prevalent
for solving natural language processing tasks. While effective, it can still require a large …
for solving natural language processing tasks. While effective, it can still require a large …