相关论文: Learning Speech Representations with Variational P…

Prediction is a fundamental capability of all living organisms, and has been proposed as an objective for learning sensory representations. Recent work demonstrates that in primate visual systems, prediction is facilitated by neural…

An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings that, as we illustrate, prevent them from fully realizing…

Unsupervised representation learning aims at describing raw data efficiently to solve various downstream tasks. It has been approached with many techniques, such as manifold learning, diffusion maps, or more recently self-supervised…

Despite being trained on massive and diverse datasets, speech self-supervised encoders are generally used for downstream purposes as mere frozen feature extractors or model initializers before fine-tuning. The former severely limits the…

State-of-the-art pretrained language models tend to perform below their capabilities when applied out-of-the-box on tasks that require understanding and working with numbers. Recent work suggests two main reasons for this: (1) popular…

We propose methods to strengthen the invariance properties of representations obtained by contrastive learning. While existing approaches implicitly induce a degree of invariance as representations are learned, we look to more directly…

Predictive coding (PC) is an influential computational model of visual learning and inference in the brain. Classical PC was proposed as a top-down generative model, where the brain actively predicts upcoming visual inputs, and inference…

This dissertation establishes the contexture theory to mathematically characterize the mechanism of representation learning, or pretraining. Despite the remarkable empirical success of foundation models, it is not very clear what…

The increasingly stringent requirement on quality-of-experience in 5G/B5G communication systems has led to the emerging neural speech enhancement techniques, which however have been developed in isolation from the existing expert-rule based…

Phrase representations play an important role in data science and natural language processing, benefiting various tasks like Entity Alignment, Record Linkage, Fuzzy Joins, and Paraphrase Classification. The current state-of-the-art method…

The unsupervised Pretraining method has been widely used in aiding human action recognition. However, existing methods focus on reconstructing the already present frames rather than generating frames which happen in future.In this paper, We…

Pre-training and representation learning have been playing an increasingly important role in modern speech processing. Nevertheless, different applications have been relying on different foundation models, since predominant pre-training…

Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition…

One of the roadblocks for training generalist robotic models today is heterogeneity. Previous robot learning methods often collect data to train with one specific embodiment for one task, which is expensive and prone to overfitting. This…

Learning human preferences in language models remains fundamentally challenging, as reward modeling relies on subtle, subjective comparisons or shades of gray rather than clear-cut labels. This study investigates the limits of current…

Large language models (LLMs) have achieved remarkable success, yet aligning their generations with human preferences remains a critical challenge. Existing approaches to preference modeling often rely on an explicit or implicit reward…

Recent work in visual representation learning for robotics demonstrates the viability of learning from large video datasets of humans performing everyday tasks. Leveraging methods such as masked autoencoding and contrastive learning, these…

Modern data-driven machine learning system designs exploit inductive biases in architectural structure, invariance and equivariance requirements, task-specific loss functions, and computational optimization tools. Previous works have…

Though offering amazing contextualized token-level representations, current pre-trained language models take less attention on accurately acquiring sentence-level representation during their self-supervised pre-training. However,…

The learning of interpretable representations from raw data presents significant challenges for time series data like speech. In this work, we propose a relevance weighting scheme that allows the interpretation of the speech representations…