Related papers: RegaVAE: A Retrieval-Augmented Gaussian Mixture Va…

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…

Clinical text improvement is vital for healthcare efficiency but remains difficult due to limited high-quality data and the complex constraints of medical documentation. While Large Language Models (LLMs) show promise, current approaches…

Parametric language models (LMs), which are trained on vast amounts of web data, exhibit remarkable flexibility and capability. However, they still face practical challenges such as hallucinations, difficulty in adapting to new data…

We present a novel introspective variational autoencoder (IntroVAE) model for synthesizing high-resolution photographic images. IntroVAE is capable of self-evaluating the quality of its generated samples and improving itself accordingly.…

Syntactic information contains structures and rules about how text sentences are arranged. Incorporating syntax into text modeling methods can potentially benefit both representation learning and generation. Variational autoencoders (VAEs)…

The vector quantization is a widely used method to map continuous representation to discrete space and has important application in tokenization for generative mode, bottlenecking information and many other tasks in machine learning. Vector…

Large language models (LLMs) achieve remarkable performance across domains but remain prone to hallucinations and inconsistencies. Retrieval-augmented generation (RAG) mitigates these issues by augmenting model inputs with relevant…

Recently, variational auto-encoder (VAE) based approaches have made impressive progress on improving the diversity of generated responses. However, these methods usually suffer the cost of decreased relevance accompanied by diversity…

Retrieval-augmented generation (RAG) has shown impressive capability in providing reliable answer predictions and addressing hallucination problems. A typical RAG implementation uses powerful retrieval models to extract external information…

This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance semantic understanding and knowledge scheduling efficiency…

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…

Extracting compact, physically interpretable representations from high-dimensional scientific data is a persistent challenge due to the complex, nonlinear structures inherent in physical systems. We propose a Gaussian Mixture Variational…

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 artificial intelligence permeates judicial forensics, ensuring the veracity and traceability of legal question answering (QA) has become critical. Conventional large language models (LLMs) are prone to hallucination, risking misleading…

Multimodal Variational Autoencoders have emerged as a popular tool to extract effective representations from rich multimodal data. However, such models rely on fusion strategies in latent space that destroy the joint statistical structure…

Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. However, even the most advanced LLMs face challenges such as hallucinations and real-time updating of their knowledge.…

Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack of explicit…

The surrogate loss of variational autoencoders (VAEs) poses various challenges to their training, inducing the imbalance between task fitting and representation inference. To avert this, the existing strategies for VAEs focus on adjusting…

Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data. However, VAEs can suffer from an issue known as latent variable collapse (or KL loss vanishing), where the posterior collapses to the…

Unified information extraction (UIE) aims to extract diverse structured information from unstructured text. While large language models (LLMs) have shown promise for UIE, they require significant computational resources and often struggle…