相关论文: Vector Quantized Contrastive Predictive Coding for…

We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary codes. One code summarizes the specified factors of variation…

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…

The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled. Most approaches to disentanglement rely on continuous variables, both for…

Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental to modern generative modeling, yet they often suffer from training instability and "codebook collapse" due to the inherent coupling of representation learning and discrete…

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Conditional discrete generative models struggle to faithfully compose multiple input conditions. To address this, we derive a theoretically-grounded formulation for composing discrete probabilistic generative processes, with masked…

Conditional discrete generative models struggle to faithfully compose multiple input conditions. To address this, we derive a theoretically-grounded formulation for composing discrete probabilistic generative processes, with masked…

Visual autoregressive (VAR) models have recently emerged as an efficient paradigm for text-to-image generation. Despite their strong generative capability, existing VAR-based personalization methods remain limited to static settings,…

Music generated by deep learning methods often suffers from a lack of coherence and long-term organization. Yet, multi-scale hierarchical structure is a distinctive feature of music signals. To leverage this information, we propose a…

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…

For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes. However, this decomposition can fall…

Compositional generalization is a key facet of human cognition, but lacking in current AI tools such as vision-language models. Previous work examined whether a compositional tensor-based sentence semantics can overcome the challenge, but…

Several methods exist for a computer to generate music based on data including Markov chains, recurrent neural networks, recombinancy, and grammars. We explore the use of unit selection and concatenation as a means of generating music using…

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…

We propose Grid-like Code Quantization (GCQ), a brain-inspired method for compressing observation-action sequences into discrete representations using grid-like patterns in attractor dynamics. Unlike conventional vector quantization…

We present a new topic model that generates documents by sampling a topic for one whole sentence at a time, and generating the words in the sentence using an RNN decoder that is conditioned on the topic of the sentence. We argue that this…

Neural compression offers a domain-agnostic approach to creating codecs for lossy or lossless compression via deep generative models. For sequence compression, however, most deep sequence models have costs that scale with the sequence…

Consistency Training (CT) has recently emerged as a strong alternative to diffusion models for image generation. However, non-distillation CT often suffers from high variance and instability, motivating ongoing research into its training…

Analyzing sequential data is crucial in many domains, particularly due to the abundance of data collected from the Internet of Things paradigm. Time series classification, the task of categorizing sequential data, has gained prominence,…

Symbolic music generation has made significant progress, yet achieving fine-grained and flexible control over composer style remains challenging. Existing training-based methods for composer style conditioning depend on large labeled…