Related papers: Improving Pre-trained Self-Supervised Embeddings T…

Semi-supervised learning provides an expressive framework for exploiting unlabeled data when labels are insufficient. Previous semi-supervised learning methods typically match model predictions of different data-augmented views in a…

Linear probing (LP) (and $k$-NN) on the upstream dataset with labels (e.g., ImageNet) and transfer learning (TL) to various downstream datasets are commonly employed to evaluate the quality of visual representations learned via…

In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information between speech and text is rarely available during training,…

Semi-supervised learning (SSL) has demonstrated high performance in image classification tasks by effectively utilizing both labeled and unlabeled data. However, existing SSL methods often suffer from poor calibration, with models yielding…

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial…

Effective representation of data is crucial in various machine learning tasks, as it captures the underlying structure and context of the data. Embeddings have emerged as a powerful technique for data representation, but evaluating their…

Semi-supervised learning (SSL) is an efficient framework that can train models with both labeled and unlabeled data, but may generate ambiguous and non-distinguishable representations when lacking adequate labeled samples. With…

Self-supervised learning (SSL) has emerged as a powerful framework to learn representations from raw data without supervision. Yet in practice, engineers face issues such as instability in tuning optimizers and collapse of representations…

Speech enhancement and separation are two fundamental tasks for robust speech processing. Speech enhancement suppresses background noise while speech separation extracts target speech from interfering speakers. Despite a great number of…

In biomedical studies, it is often desirable to characterize the interactive mode of multiple disease outcomes beyond their marginal risk. Ising model is one of the most popular choices serving for this purpose. Nevertheless, learning…

Self-supervised learning (SSL) has proven vital in speech and audio-related applications. The paradigm trains a general model on unlabeled data that can later be used to solve specific downstream tasks. This type of model is costly to train…

Long-term training of large language models (LLMs) requires maintaining stable exploration to prevent the model from collapsing into sub-optimal behaviors. Entropy is crucial in this context, as it controls exploration and helps avoid…

Self-supervised sentence representation learning is the task of constructing an embedding space for sentences without relying on human annotation efforts. One straightforward approach is to finetune a pretrained language model (PLM) with a…

Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…

The primary goal of motion planning is to generate safe and efficient trajectories for vehicles. Traditionally, motion planning models are trained using imitation learning to mimic the behavior of human experts. However, these models often…

Self-Supervised Learning (SSL) models have demonstrated exceptional performance in various speech tasks, particularly in low-resource and multilingual domains. Recent works show that fusing diverse SSL models could achieve superior…

Despite their impressive success, training foundation models remains computationally costly. This paper investigates how to efficiently train speech foundation models with self-supervised learning (SSL) under a limited compute budget. We…

Ensembling has proven to be a powerful technique for boosting model performance, uncertainty estimation, and robustness in supervised learning. Advances in self-supervised learning (SSL) enable leveraging large unlabeled corpora for…

A major challenge in Semi-Supervised Learning (SSL) is the limited information available about the class distribution in the unlabeled data. In many real-world applications this arises from the prevalence of long-tailed distributions, where…

Self-Supervised Learning (SSL) has shown great promise in learning representations from unlabeled data. The power of learning representations without the need for human annotations has made SSL a widely used technique in real-world…