相关论文: Benchmarking Generative Latent Variable Models for…

Deep latent variable generative models based on variational autoencoder (VAE) have shown promising performance for audiovisual speech enhancement (AVSE). The underlying idea is to learn a VAEbased audiovisual prior distribution for clean…

World model-based policy evaluation is a practical proxy for testing real-world robot control by rolling out candidate actions in action-conditioned video diffusion models. As these models increasingly adopt latent diffusion modeling (LDM),…

Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…

Conversational generative vision models (CGVMs) like Visual ChatGPT (Wu et al., 2023) have recently emerged from the synthesis of computer vision and natural language processing techniques. These models enable more natural and interactive…

Predicting temporal progress from visual trajectories is important for intelligent robots that can learn, adapt, and improve. However, learning such progress estimator, or temporal value function, across different tasks and domains requires…

In this paper, we introduce the Variational Autoencoder (VAE) to an end-to-end speech synthesis model, to learn the latent representation of speaking styles in an unsupervised manner. The style representation learned through VAE shows good…

In recent years, latent variable models, such as the Conditional Variational Auto Encoder (CVAE), have been applied to both personalized and empathetic dialogue generation. Prior work have largely focused on generating diverse dialogue…

This work investigates the capabilities of current vision-language models (VLMs) in visual understanding and attribute measurement of primitive shapes using a benchmark focused on controlled 2D shape configurations with variations in…

Massive MIMO (mMIMO) systems are essential for 5G/6G networks to meet high throughput and reliability demands, with machine learning (ML)-based techniques, particularly autoencoders (AEs), showing promise for practical deployment. However,…

How effectively can LLM-based AI assistants utilize their memory (context) to perform various tasks? Traditional data benchmarks, which are often manually crafted, suffer from several limitations: they are static, susceptible to…

Vector quantization (VQ) transforms continuous image features into discrete representations, providing compressed, tokenized inputs for generative models. However, VQ-based frameworks suffer from several issues, such as non-smooth latent…

In the context of an imperfect gold standard, latent class modelling can be used to estimate accuracy of multiple medical tests. However, the conditional independence (CI) assumption is rarely thought to be clinically valid. Two models…

Multimodal Large Language Models (MLLMs) have achieved significant advancements in tasks like Visual Question Answering (VQA) by leveraging foundational Large Language Models (LLMs). However, their abilities in specific areas such as visual…

Recent work in synthetic data generation in the time-series domain has focused on the use of Generative Adversarial Networks. We propose a novel architecture for synthetically generating time-series data with the use of Variational…

In this paper, we present a multimodal and dynamical VAE (MDVAE) applied to unsupervised audio-visual speech representation learning. The latent space is structured to dissociate the latent dynamical factors that are shared between the…

Majority of the recent approaches for text-independent speaker recognition apply attention or similar techniques for aggregation of frame-level feature descriptors generated by a deep neural network (DNN) front-end. In this paper, we…

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of…

Talking face generation aims to synthesize a face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video via the given speech clip and facial image. Most existing methods mainly focus on…

As large language models achieve impressive scores on traditional benchmarks, an increasing number of researchers are becoming concerned about benchmark data leakage during pre-training, commonly known as the data contamination problem. To…

Vision-Language Models (VLMs) are increasingly applied to cultural heritage materials, from digital archives to educational platforms. This work identifies a fundamental issue in how these models interpret historical artifacts. We define…