A comprehensive overview of large language models
Large Language Models (LLMs) have recently demonstrated remarkable capabilities in
natural language processing tasks and beyond. This success of LLMs has led to a large …
natural language processing tasks and beyond. This success of LLMs has led to a large …
On the effectiveness of parameter-efficient fine-tuning
Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range
of NLP tasks. However, fine-tuning the whole model is parameter inefficient as it always …
of NLP tasks. However, fine-tuning the whole model is parameter inefficient as it always …
Exploring adapter-based transfer learning for recommender systems: Empirical studies and practical insights
Adapters, a plug-in neural network module with some tunable parameters, have emerged as
a parameter-efficient transfer learning technique for adapting pre-trained models to …
a parameter-efficient transfer learning technique for adapting pre-trained models to …
Contrastive graph prompt-tuning for cross-domain recommendation
Recommender systems commonly suffer from the long-standing data sparsity problem
where insufficient user-item interaction data limits the systems' ability to make accurate …
where insufficient user-item interaction data limits the systems' ability to make accurate …
Fusing finetuned models for better pretraining
Pretrained models are the standard starting point for training. This approach consistently
outperforms the use of a random initialization. However, pretraining is a costly endeavour …
outperforms the use of a random initialization. However, pretraining is a costly endeavour …
[HTML][HTML] AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
Large pretrained language models are widely used in downstream NLP tasks via task-
specific fine-tuning, but such procedures can be costly. Recently, Parameter-Efficient Fine …
specific fine-tuning, but such procedures can be costly. Recently, Parameter-Efficient Fine …
Cold fusion: Collaborative descent for distributed multitask finetuning
We propose a new paradigm to continually evolve pretrained models, denoted ColD Fusion.
It provides the benefits of multitask learning but leverages distributed computation with …
It provides the benefits of multitask learning but leverages distributed computation with …
Deep model fusion: A survey
Deep model fusion/merging is an emerging technique that merges the parameters or
predictions of multiple deep learning models into a single one. It combines the abilities of …
predictions of multiple deep learning models into a single one. It combines the abilities of …
MixPHM: redundancy-aware parameter-efficient tuning for low-resource visual question answering
J Jiang, N Zheng - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
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 …
paradigm for achieving state-of-the-art performance in VQA. However, as VLMs scale, it …