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

Continual learning can empower vision-language models to continuously acquire new
knowledge without the need for access to the entire historical dataset. However mitigating …

Parameter-efficient transfer learning (PETL) ie fine-tuning a small portion of parameters is an
effective strategy for adapting pre-trained models to downstream domains. To further reduce …

Large foundation models, including large language models (LLMs), vision transformers
(ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine …

Large foundation models, including large language models, vision transformers, diffusion,
and LLM-based multimodal models, are revolutionizing the entire machine learning …

Personalized Federated Continual Learning (PFCL) is a new practical scenario that poses
greater challenges in sharing and personalizing knowledge. PFCL not only relies on …

Over the past year a large body of multimodal research has emerged around zero-shot
evaluation using GPT descriptors. These studies boost the zero-shot accuracy of pretrained …

Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for
adapting large pre-trained models to downstream tasks, greatly reducing trainable …

Existing methods to fine-tune LLMs like Adapter Prefix-tuning and LoRA which introduce
extra modules or additional input sequences to inject new skills or knowledge may …

Mainstream parameter-efficient fine-tuning (PEFT) methods, such as LoRA or Adapter,
project a model's hidden states to a lower dimension, allowing pre-trained models to adapt …