Related papers: EasyTransfer -- A Simple and Scalable Deep Transfe…
Soft prompt tuning is a parameter-efficient method for adapting LLMs to specific tasks, but suffers from a lack of interpretability. Building on recent work on interpreting soft prompts (Ramati et al., 2024), we explore how training a…
Transferring knowledge from large source datasets is an effective way to fine-tune the deep neural networks of the target task with a small sample size. A great number of algorithms have been proposed to facilitate deep transfer learning,…
Trained on the large corpus, pre-trained language models (PLMs) can capture different levels of concepts in context and hence generate universal language representations. They can benefit multiple downstream natural language processing…
Deep transfer learning techniques try to tackle the limitations of deep learning, the dependency on extensive training data and the training costs, by reusing obtained knowledge. However, the current DTL techniques suffer from either…
Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large…
Semantic role labeling is a crucial task in natural language processing, enabling better comprehension of natural language. However, the lack of annotated data in multiple languages has posed a challenge for researchers. To address this, a…
Efficient path planning in robotics, particularly within large-scale, complex environments, remains a significant hurdle. While Large Language Models (LLMs) offer strong reasoning capabilities, their high computational cost and limited…
In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addresses key challenges such as resource allocation, serving…
This paper introduces a framework that leverages Large Language Models (LLMs) to answer natural language queries about General Transit Feed Specification (GTFS) data. The framework is implemented in a chatbot called TransitGPT with…
Users of cloud computing are increasingly overwhelmed with the wide range of providers and services offered by each provider. As such, many users select cloud services based on description alone. An emerging alternative is to use a decision…
This paper describes the submissions of the NiuTrans Team to the WNGT 2020 Efficiency Shared Task. We focus on the efficient implementation of deep Transformer models \cite{wang-etal-2019-learning, li-etal-2019-niutrans} using NiuTensor…
Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We…
In the era of mobile computing, deploying efficient Natural Language Processing (NLP) models in resource-restricted edge settings presents significant challenges, particularly in environments requiring strict privacy compliance, real-time…
Transfer learning has recently shown significant performance across various tasks involving deep neural networks. In these transfer learning scenarios, the prior distribution for downstream data becomes crucial in Bayesian model averaging…
Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demands low latency for LLM inference. Existing LLM serving systems use…
Traffic forecasting is crucial for intelligent transportation systems. It has experienced significant advancements thanks to the power of deep learning in capturing latent patterns of traffic data. However, recent deep-learning…
The increasing adoption of natural language processing (NLP) models across industries has led to practitioners' need for machine learning systems to handle these models efficiently, from training to serving them in production. However,…
Transfer learning (TL) is widely used in conventional hybrid automatic speech recognition (ASR) system, to transfer the knowledge from source to target language. TL can be applied to end-to-end (E2E) ASR system such as recurrent neural…
In the coming 6G era, Internet of Vehicles (IoV) has been evolving towards 6G-enabled IoV with super-high data rate, seamless networking coverage, and ubiquitous intelligence by Artificial Intelligence (AI). Transfer Learning (TL) has great…
Transfer Learning (TL) aims to transfer knowledge acquired in one problem, the source problem, onto another problem, the target problem, dispensing with the bottom-up construction of the target model. Due to its relevance, TL has gained…