Related papers: TAVAE: A VAE with Adaptable Priors Explains Contex…

The variational autoencoder (VAE) framework is a popular option for training unsupervised generative models, featuring ease of training and latent representation of data. The objective function of VAE does not guarantee to achieve the…

Humans are able to create rich representations of their external reality. Their internal representations allow for cross-modality inference, where available perceptions can induce the perceptual experience of missing input modalities. In…

Visual Prompt Tuning (VPT) adapts a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable prompt tokens into the token sequence at each layer. However, we observe that existing VPT variants often…

Predictive coding is a unifying framework for understanding perception, action and neocortical organization. In predictive coding, different areas of the neocortex implement a hierarchical generative model of the world that is learned from…

Deep generative models such as conditional variational autoencoders (CVAEs) have shown great promise for predicting trajectories of surrounding agents in autonomous vehicle planning. State-of-the-art models have achieved remarkable accuracy…

In this paper, we study two aspects of the variational autoencoder (VAE): the prior distribution over the latent variables and its corresponding posterior. First, we decompose the learning of VAEs into layerwise density estimation, and…

Remote sensing image-text retrieval plays a crucial role in remote sensing interpretation, yet remains challenging under both closed-domain and open-domain scenarios due to semantic noise and domain shifts. To address these issues, we…

Vision Transformer (ViT) based autoencoders often underutilize the global Class token and employ static attention mechanisms, limiting both generative control and optimization efficiency. This paper introduces ViTCAE, a framework that…

The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong…

As the number of fine tuning of pretrained models increased, understanding the bias of pretrained model is essential. However, there is little tool to analyse transformer architecture and the interpretation of the attention maps is still…

Deep supervised neural networks trained to classify objects have emerged as popular models of computation in the primate ventral stream. These models represent information with a high-dimensional distributed population code, implying that…

Inference for Variational Autoencoders (VAEs) consists of learning two models: (1) a generative model, which transforms a simple distribution over a latent space into the distribution over observed data, and (2) an inference model, which…

How does the brain optimize sensory information for decision-making in new tasks? One hypothesis suggests learning reduces redundancy in neural representations to improve efficiency, while another, based on Bayesian inference, predicts…

The quality of data representation in deep learning methods is directly related to the prior model imposed on the representations; however, generally used fixed priors are not capable of adjusting to the context in the data. To address this…

Generative models often incur the catastrophic forgetting problem when they are used to sequentially learning multiple tasks, i.e., lifelong generative learning. Although there are some endeavors to tackle this problem, they suffer from…

Undertaking causal inference with observational data is incredibly useful across a wide range of tasks including the development of medical treatments, advertisements and marketing, and policy making. There are two significant challenges…

Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet unsupervised…

Unsupervised representation learning via generative modeling is a staple to many computer vision applications in the absence of labeled data. Variational Autoencoders (VAEs) are powerful generative models that learn representations useful…

Multi-modal generative AI systems, such as those combining vision and language, rely on contrastive pre-training to learn representations across different modalities. While their practical benefits are widely acknowledged, a rigorous…

The neural dynamics underlying brain activity are critical to understanding cognitive processes and mental disorders. However, current voxel-based whole-brain dimensionality reduction techniques fall short of capturing these dynamics,…