English
Related papers

Related papers: GenDistiller: Distilling Pre-trained Language Mode…

200 papers

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. Due to the difficulty of obtaining high-quality human preference annotations, distilling preferences from generative LLMs has emerged…

Computation and Language · Computer Science 2026-01-21 Hongli Zhou , Hui Huang , Wei Liu , Chenglong Wang , Xingyuan Bu , Lvyuan Han , Fuhai Song , Muyun Yang , Wenhao Jiang , Hailong Cao , Tiejun Zhao

Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved in two aspects: the…

Computation and Language · Computer Science 2024-07-04 Ying Zhang , Ziheng Yang , Shufan Ji

Transformer based Very Large Language Models (VLLMs) like BERT, XLNet and RoBERTa, have recently shown tremendous performance on a large variety of Natural Language Understanding (NLU) tasks. However, due to their size, these VLLMs are…

Machine Learning · Computer Science 2020-02-20 James Yi Tian , Alexander P. Kreuzer , Pai-Hung Chen , Hans-Martin Will

Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands for pseudo-data of the previous tasks. The performance…

Computation and Language · Computer Science 2021-10-19 Han Wang , Ruiliu Fu , Chengzhang Li , Xuejun Zhang , Jun Zhou , Yonghong Yan

This paper studies the potential of distilling knowledge from pre-trained models, especially Masked Autoencoders. Our approach is simple: in addition to optimizing the pixel reconstruction loss on masked inputs, we minimize the distance…

Computer Vision and Pattern Recognition · Computer Science 2022-11-11 Yutong Bai , Zeyu Wang , Junfei Xiao , Chen Wei , Huiyu Wang , Alan Yuille , Yuyin Zhou , Cihang Xie

This work explores optimizing transformer-based language models by integrating model compression techniques with inhibitor attention, a novel alternative attention mechanism. Inhibitor attention employs Manhattan distances and ReLU…

Computation and Language · Computer Science 2025-03-21 Tony Zhang , Rickard Brännvall

Producing a large annotated speech corpus for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced, but collecting a relatively big unlabeled data set for such languages is more…

Computation and Language · Computer Science 2019-08-26 Kuan-Yu Chen , Che-Ping Tsai , Da-Rong Liu , Hung-Yi Lee , Lin-shan Lee

Self-supervised learning (SSL) has garnered significant attention in speech processing, excelling in linguistic tasks such as speech recognition. However, jointly improving the performance of pre-trained models on various downstream tasks,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-04 Tianrui Wang , Jin Li , Ziyang Ma , Rui Cao , Xie Chen , Longbiao Wang , Meng Ge , Xiaobao Wang , Yuguang Wang , Jianwu Dang , Nyima Tashi

Inspired by the great success of Masked Language Modeling (MLM) in the natural language domain, the paradigm of self-supervised pre-training and fine-tuning has also achieved remarkable progress in the field of DNA sequence modeling.…

Machine Learning · Computer Science 2025-05-28 Hexiong Yang , Mingrui Chen , Huaibo Huang , Junxian Duan , Jie Cao , Zhen Zhou , Ran He

The push to compress and impart the proficiency of Large Language Models (LLMs) into more deployable and efficient Small Language Models (SLMs) has benefited from improvements in knowledge distillation (KD) techniques. These techniques…

Artificial Intelligence · Computer Science 2025-07-02 Shreyansh Padarha

Second-pass rescoring is employed in most state-of-the-art speech recognition systems. Recently, BERT based models have gained popularity for re-ranking the n-best hypothesis by exploiting the knowledge from masked language model…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-19 Prashanth Gurunath Shivakumar , Jari Kolehmainen , Yile Gu , Ankur Gandhe , Ariya Rastrow , Ivan Bulyko

Self-supervised models for speech representation learning now see widespread use for their versatility and performance on downstream tasks, but the effect of model architecture on the linguistic information learned in their representations…

Computation and Language · Computer Science 2025-08-12 Robin Huo , Ewan Dunbar

The remarkable performance of the pre-trained language model (LM) using self-supervised learning has led to a major paradigm shift in the study of natural language processing. In line with these changes, leveraging the performance of speech…

Machine Learning · Computer Science 2021-10-22 Mun-Hak Lee , Joon-Hyuk Chang

Deep learning has significantly advanced state-of-the-art of speech recognition in the past few years. However, compared to conventional Gaussian mixture acoustic models, neural network models are usually much larger, and are therefore not…

Computation and Language · Computer Science 2016-12-22 Liang Lu , Michelle Guo , Steve Renals

Multilingual self-supervised learning (SSL) has often lagged behind state-of-the-art (SOTA) methods due to the expenses and complexity required to handle many languages. This further harms the reproducibility of SSL, which is already…

Computation and Language · Computer Science 2023-09-29 William Chen , Jiatong Shi , Brian Yan , Dan Berrebbi , Wangyou Zhang , Yifan Peng , Xuankai Chang , Soumi Maiti , Shinji Watanabe

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…

Computation and Language · Computer Science 2019-06-20 Yu-An Chung , Wei-Ning Hsu , Hao Tang , James Glass

Modern search systems use several large ranker models with transformer architectures. These models require large computational resources and are not suitable for usage on devices with limited computational resources. Knowledge distillation…

Pre-trained models have achieved remarkable success in natural language processing (NLP). However, existing pre-training methods underutilize the benefits of language understanding for generation. Inspired by the idea of Generative…

Computation and Language · Computer Science 2023-05-10 Jian Yang , Shuming Ma , Li Dong , Shaohan Huang , Haoyang Huang , Yuwei Yin , Dongdong Zhang , Liqun Yang , Furu Wei , Zhoujun Li

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

Computation and Language · Computer Science 2019-08-27 Siqi Sun , Yu Cheng , Zhe Gan , Jingjing Liu

The landscape of self-supervised learning (SSL) is currently dominated by generative approaches (e.g., MAE) that reconstruct raw low-level data, and predictive approaches (e.g., I-JEPA) that predict high-level abstract embeddings. While…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Scott C. Lowe , Anthony Fuller , Sageev Oore , Evan Shelhamer , Graham W. Taylor
‹ Prev 1 4 5 6 7 8 10 Next ›