Related papers: Local Positional Encoding for Multi-Layer Perceptr…
Graph neural networks (GNNs) are the primary tool for processing graph-structured data. Unfortunately, the most commonly used GNNs, called Message Passing Neural Networks (MPNNs) suffer from several fundamental limitations. To overcome…
The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…
Solving geometric tasks involving point clouds by using machine learning is a challenging problem. Standard feed-forward neural networks combine linear or, if the bias parameter is included, affine layers and activation functions. Their…
Recently deep learning-based methods have been applied in image compression and achieved many promising results. In this paper, we propose an improved hybrid layered image compression framework by combining deep learning and the traditional…
Medical Image Computing (MIC) is a broad research topic covering both pixel-wise (e.g., segmentation, registration) and image-wise (e.g., classification, regression) vision tasks. Effective analysis demands models that capture both global…
Estimating accurate depth from a single image is challenging because it is an ill-posed problem as infinitely many 3D scenes can be projected to the same 2D scene. However, recent works based on deep convolutional neural networks show great…
Multi-electrode arrays covering several square millimeters of neural tissue provide simultaneous access to population signals such as extracellular potentials and spiking activity of one hundred or more individual neurons. The…
A significant issue in training deep neural networks to solve supervised learning tasks is the need for large numbers of labelled datapoints. The goal of semi-supervised learning is to leverage ubiquitous unlabelled data, together with…
Structural and Positional Encodings can significantly improve the performance of Graph Neural Networks in downstream tasks. Recent literature has begun to systematically investigate differences in the structural properties that these…
Neural implicit surface reconstruction has become a new trend in reconstructing a detailed 3D shape from images. In previous methods, however, the 3D scene is only encoded by the MLPs which do not have an explicit 3D structure. To better…
Due to their weak inductive bias, Multi-Layer Perceptrons (MLPs) have subpar performance at low-compute levels compared to standard architectures such as convolution-based networks (CNN). Recent work, however, has shown that the performance…
We propose a new class of linear Transformers called FourierLearner-Transformers (FLTs), which incorporate a wide range of relative positional encoding mechanisms (RPEs). These include regular RPE techniques applied for sequential data, as…
While most successful approaches for machine reading comprehension rely on single training objective, it is assumed that the encoder layer can learn great representation through the loss function we define in the predict layer, which is…
The dominant approach in probing neural networks for linguistic properties is to train a new shallow multi-layer perceptron (MLP) on top of the model's internal representations. This approach can detect properties encoded in the model, but…
The advancement of Multimodal Large Language Models (MLLMs) has greatly accelerated the development of applications in understanding integrated texts and images. Recent works leverage image-caption datasets to train MLLMs, achieving…
High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments. To handle high-dimensional sensory inputs, existing approaches use representation learning to…
An ongoing challenge in neural information processing is: how do neurons adjust their connectivity to improve task performance over time (i.e., actualize learning)? It is widely believed that there is a consistent, synaptic-level learning…
MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transformer-based methods. However, most adopt spatial MLPs which…
Multi-Layer Perceptrons (MLP) are powerful tools for representing complex, non-linear relationships, making them essential for diverse machine learning and AI applications. Efficient hardware implementation of MLPs can be achieved through…
Convolutional neural networks use regular quadrilateral convolution kernels to extract features. Since the number of parameters increases quadratically with the size of the convolution kernel, many popular models use small convolution…