Related papers: MetaLDC: Meta Learning of Low-Dimensional Computin…

In this paper, we propose $FastDoc$ (Fast Continual Pre-training Technique using Document Level Metadata and Taxonomy), a novel, compute-efficient framework that utilizes Document metadata and Domain-Specific Taxonomy as supervision signals…

Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for…

Domain-specialized FPGAs have delivered unprecedented performance for low-latency inference across scientific and industrial workloads, yet nearly all existing accelerators assume static models trained offline, relegating learning and…

There has been a significant increase in the deployment of neural network models, presenting substantial challenges in model adaptation and fine-tuning. Efficient adaptation is crucial in maintaining model performance across diverse tasks…

Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles…

Semi-supervised anomaly detection is an approach to identify anomalies by learning the distribution of normal data. Backpropagation neural networks (i.e., BP-NNs) based approaches have recently drawn attention because of their good…

Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have…

In modern mobile applications, users frequently encounter various new contexts, necessitating on-device continual learning (CL) to ensure consistent model performance. While existing research predominantly focused on developing lightweight…

We study a new highly-practical problem setting that enables resource-constrained edge devices to adapt a pre-trained model to their local data distributions. Recognizing that device's data are likely to come from multiple latent domains…

Realtime model learning proves challenging for complex dynamical systems, such as drones flying in variable wind conditions. Machine learning technique such as deep neural networks have high representation power but is often too slow to…

Object detectors trained on large-scale RGB datasets are being extensively employed in real-world applications. However, these RGB-trained models suffer a performance drop under adverse illumination and lighting conditions. Infrared (IR)…

Few-Shot Learning (FSL) is a topic of rapidly growing interest. Typically, in FSL a model is trained on a dataset consisting of many small tasks (meta-tasks) and learns to adapt to novel tasks that it will encounter during test time. This…

While numerous methods achieving remarkable performance exist in the Object Detection literature, addressing data distribution shifts remains challenging. Continual Learning (CL) offers solutions to this issue, enabling models to adapt to…

Distributed deep learning (DDL) training systems are designed for cloud and data-center environments that assumes homogeneous compute resources, high network bandwidth, sufficient memory and storage, as well as independent and identically…

Few-Shot Learning (FSL) is a challenging task, which aims to recognize novel classes with few examples. Recently, lots of methods have been proposed from the perspective of meta-learning and representation learning. However, few works focus…

Reinforcement learning (RL) has had many successes in both "deep" and "shallow" settings. In both cases, significant hyperparameter tuning is often required to achieve good performance. Furthermore, when nonlinear function approximation is…

Existing trajectory prediction methods exhibit significant performance degradation under distribution shifts during test time. Although test-time training techniques have been explored to enable adaptation, current approaches rely on an…

The prevalence of noisy labels in real-world datasets poses a significant impediment to the effective deployment of deep learning models. While meta-learning strategies have emerged as a promising approach for addressing this challenge,…

We provide a new adaptive method for online convex optimization, MetaGrad, that is robust to general convex losses but achieves faster rates for a broad class of special functions, including exp-concave and strongly convex functions, but…

Large Multimodal Models (LMMs) often rely on in-context learning (ICL) to perform new visual question answering (VQA) tasks with minimal supervision. However, ICL performance, especially in smaller LMMs, does not always improve…