Related papers: PCAE: A Framework of Plug-in Conditional Auto-Enco…

Conditional Generative Models are now acknowledged an essential tool in Machine Learning. This paper focuses on their control. While many approaches aim at disentangling the data through the coordinate-wise control of their latent…

In this paper, we introduce ControlVAE, a novel model-based framework for learning generative motion control policies based on variational autoencoders (VAE). Our framework can learn a rich and flexible latent representation of skills and a…

Variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying…

Designing codes that combat the noise in a communication medium has remained a significant area of research in information theory as well as wireless communications. Asymptotically optimal channel codes have been developed by mathematicians…

Diffusion probabilistic models (DPMs) have shown remarkable results on various image synthesis tasks such as text-to-image generation and image inpainting. However, compared to other generative methods like VAEs and GANs, DPMs lack a…

A critical aspect of reliable communication involves the design of codes that allow transmissions to be robustly and computationally efficiently decoded under noisy conditions. Advances in the design of reliable codes have been driven by…

Controllable Text Generation (CTG) has obtained great success due to its fine-grained generation ability obtained by focusing on multiple attributes. However, most existing CTG researches overlook how to utilize the attribute entanglement…

This paper introduces a novel approach for topic modeling utilizing latent codebooks from Vector-Quantized Variational Auto-Encoder~(VQ-VAE), discretely encapsulating the rich information of the pre-trained embeddings such as the…

One of the major shortcomings of variational autoencoders is the inability to produce generations from the individual modalities of data originating from mixture distributions. This is primarily due to the use of a simple isotropic Gaussian…

We introduce the Kernel-Elastic Autoencoder (KAE), a self-supervised generative model based on the transformer architecture with enhanced performance for molecular design. KAE is formulated based on two novel loss functions: modified…

Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…

Integrating physics models within machine learning models holds considerable promise toward learning robust models with improved interpretability and abilities to extrapolate. In this work, we focus on the integration of incomplete physics…

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

Controllable Text Generation (CTG) is emerging area in the field of natural language generation (NLG). It is regarded as crucial for the development of advanced text generation technologies that better meet the specific constraints in…

We propose InsNet, an expressive insertion-based text generator with efficient training and flexible decoding (parallel or sequential). Unlike most existing insertion-based text generation works that require re-encoding of the context after…

Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…

Flow control has a great potential to contribute to the sustainable society through mitigation of environmental burden. However, high dimensional and nonlinear nature of fluid flows poses challenges in designing efficient control laws. This…

We propose the In-context Autoencoder (ICAE), leveraging the power of a large language model (LLM) to compress a long context into short compact memory slots that can be directly conditioned on by the LLM for various purposes. ICAE is first…

Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems. To address the catastrophic forgetting issue of LL, generative replay methods are widely employed to consolidate past knowledge with generated pseudo…

Effective representation learning is critical for short text clustering due to the sparse, high-dimensional and noise attributes of short text corpus. Existing pre-trained models (e.g., Word2vec and BERT) have greatly improved the…