English
Related papers

Related papers: Kformer: Knowledge Injection in Transformer Feed-F…

200 papers

Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network…

Computation and Language · Computer Science 2023-06-06 Wangchunshu Zhou , Ronan Le Bras , Yejin Choi

Typical technique in knowledge distillation (KD) is regularizing the learning of a limited capacity model (student) by pushing its responses to match a powerful model's (teacher). Albeit useful especially in the penultimate layer and…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Ada Gorgun , Yeti Z. Gurbuz , A. Aydin Alatan

Transformers have been successfully applied to sequential, auto-regressive tasks despite being feedforward networks. Unlike recurrent neural networks, Transformers use attention to capture temporal relations while processing input tokens in…

Machine Learning · Computer Science 2021-01-26 Angela Fan , Thibaut Lavril , Edouard Grave , Armand Joulin , Sainbayar Sukhbaatar

We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We focus on the Transformers for our…

Computation and Language · Computer Science 2019-09-05 Elena Voita , Rico Sennrich , Ivan Titov

Deep learning methods usually require a large amount of training data and lack interpretability. In this paper, we propose a novel knowledge distillation and model interpretation framework for medical image classification that jointly…

Computer Vision and Pattern Recognition · Computer Science 2022-01-13 Thanh Nguyen-Duc , He Zhao , Jianfei Cai , Dinh Phung

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

Machine Learning (ML) models are very effective in many learning tasks, due to the capability to extract meaningful information from large data sets. Nevertheless, there are learning problems that cannot be easily solved relying on pure…

Machine Learning · Computer Science 2021-01-29 Andrea Borghesi , Federico Baldo , Michele Lombardi , Michela Milano

Diffusion Transformer(DiT) based video generation models have recently achieved impressive visual quality and temporal coherence, but they still frequently violate basic physical laws and commonsense dynamics, revealing a lack of explicit…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Selena Song , Ziming Xu , Zijun Zhang , Kun Zhou , Jiaxian Guo , Lianhui Qin , Biwei Huang

Pre-trained language models (PLMs) contain vast amounts of factual knowledge, but how the knowledge is stored in the parameters remains unclear. This paper delves into the complex task of understanding how factual knowledge is stored in…

Computation and Language · Computer Science 2023-12-21 Yuheng Chen , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

In the era of deep learning, the increasing number of pre-trained models available online presents a wealth of knowledge. These models, developed with diverse architectures and trained on varied datasets for different tasks, provide unique…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Yimu Wang , Weiming Zhuang , Chen Chen , Jiabo Huang , Jingtao Li , Lingjuan Lyu

Communication via natural language is a key aspect of machine intelligence, and it requires computational models to learn and reason about world concepts, with varying levels of supervision. Significant progress has been made on…

Computation and Language · Computer Science 2023-12-19 Prateek Chhikara , Jiarui Zhang , Filip Ilievski , Jonathan Francis , Kaixin Ma

Understanding how knowledge is distributed across the layers of generative models is crucial for improving interpretability, controllability, and adaptation. While prior work has explored knowledge localization in UNet-based architectures,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Arman Zarei , Samyadeep Basu , Keivan Rezaei , Zihao Lin , Sayan Nag , Soheil Feizi

Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This way would not work as expected due to the intermediate…

Computation and Language · Computer Science 2022-07-01 Jingping Liu , Yuqiu Song , Kui Xue , Hongli Sun , Chao Wang , Lihan Chen , Haiyun Jiang , Jiaqing Liang , Tong Ruan

The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-11 Axel Berg , Mark O'Connor , Miguel Tairum Cruz

Deep learning models have set benchmark results in various Natural Language Processing tasks. However, these models require an enormous amount of training data, which is infeasible in many practical problems. While various techniques like…

Machine Learning · Computer Science 2021-12-20 K. M. Annervaz , Pritam Kumar Nath , Ambedkar Dukkipati

Despite the success of Transformer models in vision and language tasks, they often learn knowledge from enormous data implicitly and cannot utilize structured input data directly. On the other hand, structured learning approaches such as…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Xuehai He , Xin Eric Wang

In artificial intelligence (AI), knowledge is the information required by an intelligent system to accomplish tasks. While traditional knowledge bases use discrete, symbolic representations, detecting knowledge encoded in the continuous…

Computation and Language · Computer Science 2021-04-20 Gang Chen , Maosong Sun , Yang Liu

In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Andrew Jackson

Transformer model architectures have garnered immense interest lately due to their effectiveness across a range of domains like language, vision and reinforcement learning. In the field of natural language processing for example,…

Machine Learning · Computer Science 2022-03-15 Yi Tay , Mostafa Dehghani , Dara Bahri , Donald Metzler

Neural machine translation has achieved promising results on many translation tasks. However, previous studies have shown that neural models induce a non-smooth representation space, which harms its generalization results. Recently, kNN-MT…

Computation and Language · Computer Science 2023-06-13 Wenhao Zhu , Jingjing Xu , Shujian Huang , Lingpeng Kong , Jiajun Chen