Related papers: HiD-VAE: Interpretable Generative Recommendation v…
Verification is a key bottleneck in improving inference speed while maintaining distribution fidelity in Speculative Decoding. Recent work has shown that sequence-level verification leads to a higher number of accepted tokens compared to…
Prompt-based continual learning is an emerging direction in leveraging pre-trained knowledge for downstream continual learning, and has almost reached the performance pinnacle under supervised pre-training. However, our empirical research…
Information bottleneck (IB) principle [1] has become an important element in information-theoretic analysis of deep models. Many state-of-the-art generative models of both Variational Autoencoder (VAE) [2; 3] and Generative Adversarial…
In this paper, we propose a novel model called Learnable VAE (L-VAE), which learns a disentangled representation together with the hyperparameters of the cost function. L-VAE can be considered as an extension of \b{eta}-VAE, wherein the…
Generative recommendation (GR) with semantic IDs (SIDs) has emerged as a promising alternative to traditional recommendation approaches due to its performance gains, capitalization on semantic information provided through language model…
Generative retrieval for search and recommendation is a promising paradigm for retrieving items, offering an alternative to traditional methods that depend on external indexes and nearest-neighbor searches. Instead, generative models…
Generative models, such as Variational Auto-Encoder (VAE) and Generative Adversarial Network (GAN), have been successfully applied in sequential recommendation. These methods require sampling from probability distributions and adopt…
Generative models such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have shown promise in sequential recommendation tasks. However, they face challenges, including posterior collapse and limited…
In recent years, substantial research efforts have been devoted to enhancing sequential recommender systems by integrating abundant side information with ID-based collaborative information. This study specifically focuses on leveraging the…
Fault intensity diagnosis (FID) plays a pivotal role in monitoring and maintaining mechanical devices within complex industrial systems. As current FID methods are based on chain of thought without considering dependencies among target…
Knowledge graph (KG) plays an increasingly important role to improve the recommendation performance and interpretability. A recent technical trend is to design end-to-end models based on information propagation schemes. However, existing…
Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image. However,…
Embedding is a useful technique to project a high-dimensional feature into a low-dimensional space, and it has many successful applications including link prediction, node classification and natural language processing. Current approaches…
Controllable data generation aims to synthesize data by specifying values for target concepts. Achieving this reliably requires modeling the underlying generative factors and their relationships. In real-world scenarios, these factors…
Disentangled representation learning aims to learn low-dimensional representations where each dimension corresponds to an underlying generative factor. While the Variational Auto-Encoder (VAE) is widely used for this purpose, most existing…
Recommender systems play important roles in various applications such as e-commerce, social media, etc. Conventional recommendation methods usually model the collaborative signals within the tabular representation space. Despite the…
Variational autoencoders (VAEs), as well as other generative models, have been shown to be efficient and accurate for capturing the latent structure of vast amounts of complex high-dimensional data. However, existing VAEs can still not…
Generative Recommendation (GR) has emerged as a new paradigm in recommender systems. This approach relies on quantized representations to discretize item features, modeling users' historical interactions as sequences of discrete tokens.…
Generative recommendation (GR) models generate items by autoregressively producing a sequence of discrete tokens that jointly index the target item. However, this autoregressive generation process also induces a structured decoding space…
The rise of deep learning applications in the fashion industry has fueled advances in curating large-scale datasets to build applications for product design, image retrieval, and recommender systems. In this paper, the author proposes using…