Related papers: Discrete Auto-regressive Variational Attention Mod…
Latent variable models for text, when trained successfully, accurately model the data distribution and capture global semantic and syntactic features of sentences. The prominent approach to train such models is variational autoencoders…
As Vision-Language Models (VLMs) become increasingly sophisticated and widely used, it becomes more and more crucial to understand their decision-making process. Traditional explainability methods, designed for classification tasks,…
In Emotion Recognition in Conversations (ERC), the emotions of target utterances are closely dependent on their context. Therefore, existing works train the model to generate the response of the target utterance, which aims to recognise…
The Variational Autoencoder (VAE) is known to suffer from the phenomenon of \textit{posterior collapse}, where the latent representations generated by the model become independent of the inputs. This leads to degenerated representations of…
The Large Vision-Language Model (LVLM) integrates computer vision and natural language processing techniques, offering substantial application potential. However, these models demand extensive resources during inference. Adaptive attention…
We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard evidence lower bound. We provide conditions under which they recover the data distribution and learn latent features, and…
Existing video Variational Autoencoders (VAEs) generally overlook the similarity between frame contents, leading to redundant latent modeling. In this paper, we propose decoupled VAE (DeCo-VAE) to achieve compact latent representation.…
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…
The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data. However, it has thus far seen limited application to sequential data, and, as we…
Variational autoencoders (VAEs) have recently been used for unsupervised disentanglement learning of complex density distributions. Numerous variants exist to encourage disentanglement in latent space while improving reconstruction.…
One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete representation uses only a fraction of the full capacity of the codebook, also known as codebook collapse. We hypothesize that the training…
Latent diffusion has demonstrated promising results in image generation and permits efficient sampling. However, this framework might suffer from the problem of posterior collapse when applied to time series. In this paper, we first show…
Recent advancements in sequence prediction have significantly improved the accuracy of video data interpretation; however, existing models often overlook the potential of attention-based mechanisms for next-frame prediction. This study…
Diffusion models represent a new paradigm in text-to-image generation. Beyond generating high-quality images from text prompts, models such as Stable Diffusion have been successfully extended to the joint generation of semantic segmentation…
The recently proposed identifiable variational autoencoder (iVAE) framework provides a promising approach for learning latent independent components (ICs). iVAEs use auxiliary covariates to build an identifiable generation structure from…
Sequence-to-sequence (Seq2seq) models have played an important role in the recent success of various natural language processing methods, such as machine translation, text summarization, and speech recognition. However, current Seq2seq…
Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We…
Vision Transformers (ViTs) have significantly advanced computer vision, demonstrating strong performance across various tasks. However, the attention mechanism in ViTs makes each layer function as a low-pass filter, and the stacked-layer…
Variational autoencoders (VAEs) hold great potential for modelling text, as they could in theory separate high-level semantic and syntactic properties from local regularities of natural language. Practically, however, VAEs with…
Variational Autoencoders (VAEs), as a form of deep generative model, have been widely used in recent years, and shown great great peformance in a number of different domains, including image generation and anomaly detection, etc.. This…