Related papers: Multiple-Exit Tuning: Towards Inference-Efficient …

More music foundation models are recently being released, promising a general, mostly task independent encoding of musical information. Common ways of adapting music foundation models to downstream tasks are probing and fine-tuning. These…

Recently, Vision Transformer (ViT) has achieved promising performance in image recognition and gradually serves as a powerful backbone in various vision tasks. To satisfy the sequential input of Transformer, the tail of ViT first splits…

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 for downstream tasks due to their high computational and…

The inference of large language models imposes significant computational workloads, often requiring the processing of billions of parameters. Although early-exit strategies have proven effective in reducing computational demands by halting…

Large-scale pre-trained models have achieved remarkable success in various computer vision tasks. A standard approach to leverage these models is to fine-tune all model parameters for downstream tasks, which poses challenges in terms of…

Different languages have distinct phonetic systems and vary in their prosodic features making it challenging to develop a Text-to-Speech (TTS) model that can effectively synthesise speech in multilingual settings. Furthermore, TTS…

Vision Transformers (ViTs) have emerged as a foundational model in computer vision, excelling in generalization and adaptation to downstream tasks. However, deploying ViTs to support diverse resource constraints typically requires…

Deep learning models are increasingly utilized on resource-constrained edge devices for real-time data analytics. Recently, Vision Transformer and their variants have shown exceptional performance in various computer vision tasks. However,…

Parameter-efficient fine-tuning (PEFT) techniques, such as adapter tuning, aim to fine-tune a pre-trained language model (PLM) using a minimal number of parameters for a specific task or profile. Although adapter tuning provides increased…

Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit…

Recent work has explored the potential to adapt a pre-trained vision transformer (ViT) by updating only a few parameters so as to improve storage efficiency, called parameter-efficient transfer learning (PETL). Current PETL methods have…

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However,…

Parameter-efficient fine-tuning (PEFT) has attracted significant attention due to the growth of pre-trained model sizes and the need to fine-tune (FT) them for superior downstream performance. Despite a surge in new PEFT methods, a…

Considering deep neural networks as manifold mappers, the pretrain-then-fine-tune paradigm can be interpreted as a two-stage process: pretrain establishes a broad knowledge base, and fine-tune adjusts the model parameters to activate…

Parameter-Efficient Fine-Tuning (PEFT) is widely used for adapting Large Language Models (LLMs) for various tasks. Recently, there has been an increasing demand for fine-tuning a single LLM for multiple tasks because it requires overall…

Deep neural networks have become larger over the years with increasing demand of computational resources for inference; incurring exacerbate costs and leaving little room for deployment on devices with limited battery and other resources…

The success of large-scale pre-trained models has established fine-tuning as a standard method for achieving significant improvements in downstream tasks. However, fine-tuning the entire parameter set of a pre-trained model is costly.…

Recently, foundation models based on Vision Transformers (ViTs) have become widely available. However, their fine-tuning process is highly resource-intensive, and it hinders their adoption in several edge or low-energy applications. To this…

Early exiting is an effective paradigm for improving the inference efficiency of deep networks. By constructing classifiers with varying resource demands (the exits), such networks allow easy samples to be output at early exits, removing…

Semantic segmentation arises as the backbone of many vision systems, spanning from self-driving cars and robot navigation to augmented reality and teleconferencing. Frequently operating under stringent latency constraints within a limited…