Convolutional neural networks (CNNs) were inspired by early findings in the study of
biological vision. They have since become successful tools in computer vision and state-of …

Artificial neural networks (ANNs) inspired by biology are beginning to be widely used to
model behavioural and neural data, an approach we call 'neuroconnectionism'. ANNs have …

Time series analysis is of immense importance in extensive applications, such as weather
forecasting, anomaly detection, and action recognition. This paper focuses on temporal …

The recent boom of linear forecasting models questions the ongoing passion for
architectural modifications of Transformer-based forecasters. These forecasters leverage …

In this paper, we explore a novel knowledge-transfer task, termed as Deep Model
Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous …

Vision transformers (ViT) have shown promise in various vision tasks while the U-Net based
on a convolutional neural network (CNN) remains dominant in diffusion models. We design …

Convolutional neural networks (CNNs) have so far been the de-facto model for visual data.
Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or …

Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of
data distributions when performing zero-shot inference (ie, without fine-tuning on a specific …

Time series analysis is widely used in extensive areas. Recently, to reduce labeling
expenses and benefit various tasks, self-supervised pre-training has attracted immense …

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 …