Related papers: Latent Neural Cellular Automata for Resource-Effic…

Adapting Large Language Models (LLMs) to downstream tasks using Reinforcement Learning (RL) has proven to be an effective approach. However, LLMs do not inherently define the structure of an agent for RL training, particularly in terms of…

The Transformer architecture has opened a new paradigm in the domain of deep learning with its ability to model long-range dependencies and capture global context and has outpaced the traditional Convolution Neural Networks (CNNs) in many…

How to aggregate spatial information plays an essential role in learning-based image restoration. Most existing CNN-based networks adopt static convolutional kernels to encode spatial information, which cannot aggregate spatial information…

Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of…

We propose a learnable variational model that learns the features and leverages complementary information from both image and measurement domains for image reconstruction. In particular, we introduce a learned alternating minimization…

The full-size MLPs and the projection layers in attention introduce tremendous model sizes of large language models (LLMs), consuming extensive computational resources in pre-training. We empirically observe that the activations of…

Current Dynamic Texture Synthesis (DyTS) models can synthesize realistic videos. However, they require a slow iterative optimization process to synthesize a single fixed-size short video, and they do not offer any post-training control over…

Large Language Models (LLMs) are known for their expensive and time-consuming training. Thus, oftentimes, LLMs are fine-tuned to address a specific task, given the pretrained weights of a pre-trained LLM considered a foundation model. In…

We introduce Latent Meaning Cells, a deep latent variable model which learns contextualized representations of words by combining local lexical context and metadata. Metadata can refer to granular context, such as section type, or to more…

Machine learning (ML) tools such as encoder-decoder convolutional neural networks (CNN) can represent incredibly complex nonlinear functions which map between combinations of images and scalars. For example, CNNs can be used to map…

Training reinforcement learning (RL) agents often requires significant computational resources and prolonged training durations. To address this challenge, we build upon prior work that introduced a neural architecture with…

Medical visual question answering (Med-VQA) aims to automate the prediction of correct answers for medical images and questions, thereby assisting physicians in reducing repetitive tasks and alleviating their workload. Existing approaches…

Cellular automata (CA) are simulation models that can produce complex emergent behaviors from simple local rules. Although state-of-the-art GPU solutions are already fast due to their data-parallel nature, their performance can rapidly…

This paper presents solutions to Density Classification Task (DCT) using a variant of Cellular Automata (CA) called Programmable Cellular Automata (PCA). The translation property as well as the density preserving property of fundamental CA…

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this…

Cellular automata (CA), originally developed as computational models of natural processes, have become a central subject in the study of complex systems and generative visual forms. Among them, the Ulam-Warburton Cellular Automaton (UWCA)…

The Reservoir Computing (RC) paradigm utilizes a dynamical system, i.e., a reservoir, and a linear classifier, i.e., a read-out layer, to process data from sequential classification tasks. In this paper the usage of Cellular Automata (CA)…

Low-dose computed tomography (LDCT) aims to minimize the radiation exposure to patients while maintaining diagnostic image quality. However, traditional CT reconstruction algorithms often struggle with the ill-posed nature of the problem,…

Reconstructing degraded images is a critical task in image processing. Although CNN and Transformer-based models are prevalent in this field, they exhibit inherent limitations, such as inadequate long-range dependency modeling and high…

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…