We present ShapeFormer, a transformer-based network that produces a distribution of
object completions, conditioned on incomplete, and possibly noisy, point clouds. The …

Vector quantization, renowned for its unparalleled feature compression capabilities, has
been a prominent topic in signal processing and machine learning research for several …

We introduce dGSLM, the first “textless” model able to generate audio samples of naturalistic
spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with …

Automatic Music Transcription (AMT), inferring musical notes from raw audio, is a
challenging task at the core of music understanding. Unlike Automatic Speech Recognition …

The success of deep learning comes from its ability to capture the hierarchical structure of
data by learning high-level representations defined in terms of low-level ones. In this paper …

Human activity recognition (HAR) in wearable and ubiquitous computing typically involves
translating sensor readings into feature representations, either derived through dedicated …

We investigate the possibility of forcing a self-supervised model trained using a contrastive
predictive loss to extract slowly varying latent representations. Rather than producing …

Neuroscientists and neuroengineers have long relied on multielectrode neural recordings to
study the brain. However, in a typical experiment, many factors corrupt neural recordings …

Compressing self-supervised models has become increasingly necessary, as self-
supervised models become larger. While previous approaches have primarily focused on …

Tokenization algorithms that merge the units of a base vocabulary into larger, variable-rate
units have become standard in natural language processing tasks. This idea, however, has …