Related papers: Conditional Latent Coding with Learnable Synthesiz…

Currently, image-denoising methods based on deep learning cannot adequately reconcile contextual semantic information and spatial details. To take these information optimizations into consideration, in this paper, we propose a Context-Space…

Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desideratum in conditional synthesis is to achieve high…

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

Identifying meaningful and independent factors of variation in a dataset is a challenging learning task frequently addressed by means of deep latent variable models. This task can be viewed as learning symmetry transformations preserving…

We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the…

In learning-based approaches to image compression, codecs are developed by optimizing a computational model to minimize a rate-distortion objective. Currently, the most effective learned image codecs take the form of an entropy-constrained…

To enhance image compression performance, recent deep neural network-based research can be divided into three categories: a learnable codec, a postprocessing network, and a compact representation network. The learnable codec has been…

Semantic communications has received growing interest since it can remarkably reduce the amount of data to be transmitted without missing critical information. Most existing works explore the semantic encoding and transmission for text and…

Conditional image synthesis is a crucial task with broad applications, such as artistic creation and virtual reality. However, current generative methods are often task-oriented with a narrow scope, handling a restricted condition with…

Continual learning (CL) is designed to learn new tasks while preserving existing knowledge. Replaying samples from earlier tasks has proven to be an effective method to mitigate the forgetting of previously acquired knowledge. However, the…

Consistency models have emerged as a promising alternative to diffusion models, offering high-quality generative capabilities through single-step sample generation. However, their application to multi-domain image translation tasks, such as…

Semantic image synthesis aims at generating photorealistic images from semantic layouts. Previous approaches with conditional generative adversarial networks (GAN) show state-of-the-art performance on this task, which either feed the…

Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious,…

Compressive learning (CL) is an emerging framework that integrates signal acquisition via compressed sensing (CS) and machine learning for inference tasks directly on a small number of measurements. It can be a promising alternative to…

In this paper, we introduce a novel approach for systematically solving dataset condensation problem in an efficient manner by exploiting the regularity in a given dataset. Instead of condensing the dataset directly in the original input…

Multilinear Compressive Learning (MCL) is an efficient signal acquisition and learning paradigm for multidimensional signals. The level of signal compression affects the detection or classification performance of a MCL model, with higher…

Integrating Large Language Models (LLMs) with existing Knowledge Graph (KG) databases presents a promising avenue for enhancing LLMs' efficacy and mitigating their "hallucinations". Given that most KGs reside in graph databases accessible…

To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity. This work introduces a…

The latent representation in learned image compression encompasses channel-wise, local spatial, and global spatial correlations, which are essential for the entropy model to capture for conditional entropy minimization. Efficiently…

Generalizing models trained on normal visual conditions to target domains under adverse conditions is demanding in the practical systems. One prevalent solution is to bridge the domain gap between clear- and adverse-condition images to make…