Dubbed “the successor to the mobile Internet,” the concept of the Metaverse has grown in
popularity. While there exist lite versions of the Metaverse today, they are still far from …

Recent success of deep learning is largely attributed to the sheer amount of data used for
training deep neural networks. Despite the unprecedented success, the massive data …

The rapid advancement of chat-based language models has led to remarkable progress in
complex task-solving. However, their success heavily relies on human input to guide the …

State-of-the-art distillation methods are mainly based on distilling deep features from
intermediate layers, while the significance of logit distillation is greatly overlooked. To …

This article addresses the problem of distilling knowledge from a large teacher model to a
slim student network for LiDAR semantic segmentation. Directly employing previous …

Unlike existing knowledge distillation methods focus on the baseline settings, where the
teacher models and training strategies are not that strong and competing as state-of-the-art …

We present a novel class incremental learning approach based on deep neural networks,
which continually learns new tasks with limited memory for storing examples in the previous …

Transformers have been recently adapted for large scale image classification, achieving
high scores shaking up the long supremacy of convolutional neural networks. However the …

This chapter provides approaches to the problem of quantizing the numerical values in deep
Neural Network computations, covering the advantages/disadvantages of current methods …

In this paper, we explore a novel and ambitious knowledge-transfer task, termed Knowledge
Factorization (KF). The core idea of KF lies in the modularization and assemblability of …