English
Related papers

Related papers: MiniLMv2: Multi-Head Self-Attention Relation Disti…

200 papers

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

Computation and Language · Computer Science 2022-05-17 Gerard Sant , Gerard I. Gállego , Belen Alastruey , Marta R. Costa-Jussà

Neural approaches to ranking based on pre-trained language models are highly effective in ad-hoc search. However, the computational expense of these models can limit their application. As such, a process known as knowledge distillation is…

Information Retrieval · Computer Science 2024-11-05 Vishakha Suresh Kalal , Andrew Parry , Sean MacAvaney

Knowledge Distillation (KD) has been considered as a key solution in model compression and acceleration in recent years. In KD, a small student model is generally trained from a large teacher model by minimizing the divergence between the…

Machine Learning · Computer Science 2021-11-16 Raed Alharbi , Minh N. Vu , My T. Thai

In this work, we propose an architecture of LLM Modules that enables the transfer of knowledge from a large pre-trained model to a smaller model using an Enhanced Cross-Attention mechanism. In the proposed scheme, the Qwen2-1.5B model is…

Computation and Language · Computer Science 2025-02-13 Konstantin Kolomeitsev

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from the input embeddings with large input…

Computation and Language · Computer Science 2021-02-09 Sanqiang Zhao , Raghav Gupta , Yang Song , Denny Zhou

Despite the fact that Transformers perform well in NLP tasks, recent studies suggest that self-attention is theoretically limited in learning even some regular and context-free languages. These findings motivated us to think about their…

Computation and Language · Computer Science 2023-10-20 Shunjie Wang , Shane Steinert-Threlkeld

Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM. However, current distillation methods require similar tokenizers between the teacher and the student,…

Computation and Language · Computer Science 2025-10-27 Benjamin Minixhofer , Ivan Vulić , Edoardo Maria Ponti

In this work, we present a novel method, named AV2vec, for learning audio-visual speech representations by multimodal self-distillation. AV2vec has a student and a teacher module, in which the student performs a masked latent feature…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-07 Jing-Xuan Zhang , Genshun Wan , Zhen-Hua Ling , Jia Pan , Jianqing Gao , Cong Liu

While Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks, their substantial computational requirements and restricted number of calls constrain their practical utility, especially in…

Machine Learning · Computer Science 2024-05-07 Maryam Hashemzadeh , Elias Stengel-Eskin , Sarath Chandar , Marc-Alexandre Cote

The reward model (RM), as the core component of reinforcement learning from human feedback (RLHF) for large language models (LLMs), responsible for providing reward signals to generated responses. However, the mainstream discriminative…

Computation and Language · Computer Science 2026-01-14 Jianxiang Zang

This study investigates small-scale pretraining for Small Language Models (SLMs) to enable efficient use of limited data and compute, improve accessibility in low-resource settings and reduce costs. To enhance long-context extrapolation in…

Machine Learning · Computer Science 2026-01-01 Ruizhe Huang , Kexuan Zhang , Yihao Fang , Baifeng Yu

Tiny, causal models are crucial for embedded audio machine learning applications. Model compression can be achieved via distilling knowledge from a large teacher into a smaller student model. In this work, we propose a novel two-step…

Sound · Computer Science 2023-09-18 Rayan Daod Nathoo , Mikolaj Kegler , Marko Stamenovic

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…

Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily…

Machine Learning · Computer Science 2019-04-22 Xiao Jin , Baoyun Peng , Yichao Wu , Yu Liu , Jiaheng Liu , Ding Liang , Junjie Yan , Xiaolin Hu

Neural Machine Translation (NMT) models achieve state-of-the-art performance on many translation benchmarks. As an active research field in NMT, knowledge distillation is widely applied to enhance the model's performance by transferring…

Computation and Language · Computer Science 2021-05-28 Fusheng Wang , Jianhao Yan , Fandong Meng , Jie Zhou

Knowledge distillation is of key importance to launching multilingual pre-trained language models for real applications. To support cost-effective language inference in multilingual settings, we propose AMTSS, an adaptive multi-teacher…

Computation and Language · Computer Science 2023-05-16 Qianglong Chen , Feng Ji , Feng-Lin Li , Guohai Xu , Ming Yan , Ji Zhang , Yin Zhang

Video-based action recognition is one of the most popular topics in computer vision. With recent advances of selfsupervised video representation learning approaches, action recognition usually follows a two-stage training framework, i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2022-05-03 Yang Zhou , Zhanhao He , Keyu Lu , Guanhong Wang , Gaoang Wang

In visual tasks, large teacher models capture essential features and deep information, enhancing performance. However, distilling this information into smaller student models often leads to performance loss due to structural differences and…

Computer Vision and Pattern Recognition · Computer Science 2024-05-17 Zhiwei Wang , Jun Huang , Longhua Ma , Chengyu Wu , Hongyu Ma

Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-28 Rui Wang , Junyi Ao , Long Zhou , Shujie Liu , Zhihua Wei , Tom Ko , Qing Li , Yu Zhang

Feature regression is a simple way to distill large neural network models to smaller ones. We show that with simple changes to the network architecture, regression can outperform more complex state-of-the-art approaches for knowledge…

Computer Vision and Pattern Recognition · Computer Science 2022-01-14 K L Navaneet , Soroush Abbasi Koohpayegani , Ajinkya Tejankar , Hamed Pirsiavash