Related papers: Convolutional Gated MLP: Combining Convolutions & …
Graph neural networks (GNNs) have achieved great success in many graph-based applications. However, the enormous size and high sparsity level of graphs hinder their applications under industrial scenarios. Although some scalable GNNs are…
Solving partially-observable Markov decision processes (POMDPs) is critical when applying reinforcement learning to real-world problems, where agents have an incomplete view of the world. We present graph convolutional memory (GCM), the…
We introduce PointConvFormer, a novel building block for point cloud based deep network architectures. Inspired by generalization theory, PointConvFormer combines ideas from point convolution, where filter weights are only based on relative…
Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is limited by the number of message passing layers. To increase the receptive field, Graph…
We propose RepMLP, a multi-layer-perceptron-style neural network building block for image recognition, which is composed of a series of fully-connected (FC) layers. Compared to convolutional layers, FC layers are more efficient, better at…
Vision-Language Models (vLLMs) have emerged as powerful architectures for joint reasoning over visual and textual inputs, enabling breakthroughs in image captioning, cross modal retrieval, and multimodal dialogue. However, as these models…
In this contribution, we show how to incorporate prior knowledge to a deep neural network architecture in a principled manner. We enforce feature space invariances using a novel layer based on invariant integration. This allows us to…
Document classification is a challenging task with important applications. The deep learning approaches to the problem have gained much attention recently. Despite the progress, the proposed models do not incorporate the knowledge of the…
We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior works, which were trained to optimize the weights of a pre-selected set of…
LiDAR-generated point clouds are crucial for perceiving outdoor environments. The segmentation of point clouds is also essential for many applications. Previous research has focused on using self-attention and convolution (local attention)…
Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…
We introduce the first multitasking vision transformer adapters that learn generalizable task affinities which can be applied to novel tasks and domains. Integrated into an off-the-shelf vision transformer backbone, our adapters can…
Multi-view sequential learning is a fundamental problem in machine learning dealing with multi-view sequences. In a multi-view sequence, there exists two forms of interactions between different views: view-specific interactions and…
We study the \emph{in-context learning} (ICL) ability of a \emph{Linear Transformer Block} (LTB) that combines a linear attention component and a linear multi-layer perceptron (MLP) component. For ICL of linear regression with a Gaussian…
Vision Transformer and its variants have demonstrated great potential in various computer vision tasks. But conventional vision transformers often focus on global dependency at a coarse level, which suffer from a learning challenge on…
Convolutional Neural Networks (CNNs) have achieved outstanding performance on image processing challenges. Actually, CNNs imitate the typically developed human brain structures at the micro-level (Artificial neurons). At the same time, they…
Traditional self-attention mechanisms in convolutional networks tend to use only the output of the previous layer as input to the attention network, such as SENet, CBAM, etc. In this paper, we propose a new attention modification method…
Attention layers -- which map a sequence of inputs to a sequence of outputs -- are core building blocks of the Transformer architecture which has achieved significant breakthroughs in modern artificial intelligence. This paper presents a…
Transformer architectures are the backbone of the modern AI revolution. However, they are based on simply stacking the same blocks in dozens of layers and processing information sequentially from one block to another. In this paper, we…
Attention-based neural networks, such as Transformers, have become ubiquitous in numerous applications, including computer vision, natural language processing, and time-series analysis. In all kinds of attention networks, the attention maps…