9 accepted papers
Continual instruction tuning (CIT) has emerged as a promising strategy for adapting large language models (LLMs) to new tasks while preserving historical knowledge. Most existing CIT methods have focused on offline CIT (offCIT), which assumes clearly defined task boundaries and allows multiple passe
Multivariate time-series forecasting (MTSF) learns from high-dimensional covariates with strong temporal dependence, periodic structure, and cross-variable correlations. While modern pipelines often mitigate non-stationarity through instance-wise normalization and decomposition, these interventions …
Test-time adaptation (TTA) addresses the machine learning challenge of adapting models to unlabeled test data from shifting distributions in dynamic environments. A key issue in this online setting arises from using unsupervised learning techniques, which introduce explicit gradient noise that degr…
Pre-trained models based on deep neural networks hold strong potential for cross-domain adaptability. However, this potential is often impeded in online machine learning (OML) settings, where the breakdown of the independent and identically distributed (i.i.d.) assumption leads to unstable adaptatio…
Deep neural networks (DNNs) have revolutionized tasks such as image classification and speech recognition but often falter when training and test data diverge in distribution. External factors, from weather effects on images to varied speech environments, can cause this discrepancy, compromising DNN…
In the rapidly evolving field of online test-time adaptation (OTTA), effectively managing distribution shifts is a pivotal concern. State-of-the-art OTTA methodologies often face limitations such as an inadequate target domain information integration, leading to significant issues like catastrophic…
Research on personalizing neural transducer-based automatic speech recognition (ASR) systems using the text-only data is currently flourishing. Among various approaches, utilizing synthesized speech offers an advantage of adapting the entire ASR system. In this study, we explore the problem of perso…
Representation models pre-trained on unlabeled data show competitive performance in speech recognition, even when fine-tuned on small amounts of labeled data. The continual representation learning (CTRL) framework combines pre-training and continual learning methods to obtain powerful representation…
Representation-based speech recognition models have demonstrated state-of-the-art performance on downstream tasks. These models are pre-trained on large-scale unlabeled data, fine-tuned on a small amount of labeled data, and subsequently advanced via the self-training procedure by leveraging pseudo-…