English
Related papers

Related papers: Soft-TransFormers for Continual Learning

200 papers

Policy-gradient approaches to reinforcement learning have two common and undesirable overhead procedures, namely warm-start training and sample variance reduction. In this paper, we describe a reinforcement learning method based on a…

Machine Learning · Computer Science 2017-10-17 Nan Ding , Radu Soricut

Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice. We bridge this gap by analyzing standard…

Machine Learning · Computer Science 2026-05-19 Moritz Brösamle , Stephan Eckstein

Large Language Models (LLMs) herald a transformative era in artificial intelligence (AI). However, the expansive scale of data and parameters of LLMs requires high-demand computational and memory resources, restricting their accessibility…

Machine Learning · Computer Science 2024-11-26 Shengwen Ding , Chenhui Hu

Deep learning has delivered its powerfulness in many application domains, especially in image and speech recognition. As the backbone of deep learning, deep neural networks (DNNs) consist of multiple layers of various types with hundreds to…

Machine Learning · Computer Science 2017-12-14 Sheng Lin , Ning Liu , Mahdi Nazemi , Hongjia Li , Caiwen Ding , Yanzhi Wang , Massoud Pedram

Large-scale pre-training has brought unimodal fields such as computer vision and natural language processing to a new era. Following this trend, the size of multi-modal learning models constantly increases, leading to an urgent need to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Yaowei Li , Ruijie Quan , Linchao Zhu , Yi Yang

We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling…

Continual learning allows the system to learn and adapt to new tasks while retaining the knowledge acquired from previous tasks. However, deep learning models suffer from catastrophic forgetting of knowledge learned from earlier tasks while…

Machine Learning · Computer Science 2024-12-17 Dupati Srikar Chandra , P. K. Srijith , Dana Rezazadegan , Chris McCarthy

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 James Seale Smith , Leonid Karlinsky , Vyshnavi Gutta , Paola Cascante-Bonilla , Donghyun Kim , Assaf Arbelle , Rameswar Panda , Rogerio Feris , Zsolt Kira

With the tremendous success of large transformer models in natural language understanding, down-sizing them for cost-effective deployments has become critical. Recent studies have explored the low-rank weight factorization techniques which…

Computation and Language · Computer Science 2023-12-21 Rahul Chand , Yashoteja Prabhu , Pratyush Kumar

Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various downstream tasks. However, most fine-tuning approaches update all the parameters of the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-31 Junyi Peng , Themos Stafylakis , Rongzhi Gu , Oldřich Plchot , Ladislav Mošner , Lukáš Burget , Jan Černocký

Pre-trained language models (PLMs) demonstrate remarkable intelligence but struggle with emerging tasks unseen during training in real-world applications. Training separate models for each new task is usually impractical. Multi-task…

Computation and Language · Computer Science 2025-05-02 Xiao Zhang , Kangsheng Wang , Tianyu Hu , Huimin Ma

With the scale of vision Transformer-based models continuing to grow, finetuning these large-scale pretrained models for new tasks has become increasingly parameter-intensive. Visual prompt tuning is introduced as a parameter-efficient…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Runjia Zeng , Cheng Han , Qifan Wang , Chunshu Wu , Tong Geng , Lifu Huang , Ying Nian Wu , Dongfang Liu

This work proposes an unsupervised fusion framework based on deep convolutional transform learning. The great learning ability of convolutional filters for data analysis is well acknowledged. The success of convolutive features owes to…

Machine Learning · Computer Science 2020-11-10 Pooja Gupta , Jyoti Maggu , Angshul Majumdar , Emilie Chouzenoux , Giovanni Chierchia

Existing LLMs-post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT). Each paradigm presents a distinct trade-off: (1) SFT excels at mimicking demonstration data, but can lead…

Machine Learning · Computer Science 2026-05-18 Zeyu Huang , Tianhao Cheng , Zihan Qiu , Zili Wang , Yinghui Xu , Edoardo M. Ponti , Ivan Titov

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Computation and Language · Computer Science 2025-12-24 Xiang Chen , Yixin Ou , Quan Feng , Lei Li , Piji Li , Haibo Ye , Sheng-Jun Huang , Shuofei Qiao , Shumin Deng , Huajun Chen , Ningyu Zhang

Soft prompts have been recently proposed as a tool for adapting large frozen language models (LMs) to new tasks. In this work, we repurpose soft prompts to the task of injecting world knowledge into LMs. We introduce a method to train soft…

Computation and Language · Computer Science 2022-10-11 Cicero Nogueira dos Santos , Zhe Dong , Daniel Cer , John Nham , Siamak Shakeri , Jianmo Ni , Yun-hsuan Sung

There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a…

Computation and Language · Computer Science 2022-03-18 Tu Vu , Brian Lester , Noah Constant , Rami Al-Rfou , Daniel Cer

Text to speech (TTS) is a crucial task for user interaction, but TTS model training relies on a sizable set of high-quality original datasets. Due to privacy and security issues, the original datasets are usually unavailable directly.…

Machine Learning · Computer Science 2021-07-20 Zhenhou Hong , Jianzong Wang , Xiaoyang Qu , Jie Liu , Chendong Zhao , Jing Xiao

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,…

Computation and Language · Computer Science 2023-03-07 Zhen Wang , Rameswar Panda , Leonid Karlinsky , Rogerio Feris , Huan Sun , Yoon Kim

Continual learning requires the model to learn multiple tasks sequentially. In continual learning, the model should possess the ability to maintain its performance on old tasks (stability) and the ability to adapt to new tasks continuously…

Machine Learning · Computer Science 2024-04-04 Yan-Shuo Liang , Wu-Jun Li