Related papers: Knowledge-driven Augmentation and Retrieval for In…

Test-time adaptation (TTA) has emerged as a promising paradigm for vision-language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works have focused on backpropagation-free TTA methods that rely on…

Open-domain Question Answering (OpenQA) aims at answering factual questions with an external large-scale knowledge corpus. However, real-world knowledge is not static; it updates and evolves continually. Such a dynamic characteristic of…

Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled…

Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a foundation for personalized education. While traditional deep learning models achieve high accuracy, they often lack…

Incremental learning is the ability of systems to acquire knowledge over time, enabling their adaptation and generalization to novel tasks. It is a critical ability for intelligent, real-world systems, especially when data changes…

Multivariate Long Sequence Time-series Forecasting (LSTF) has been a critical task across various real-world applications. Recent advancements focus on the application of transformer architectures attributable to their ability to capture…

Data augmentation integrates domain knowledge into a dataset by making domain-informed modifications to existing data points. For example, image data can be augmented by duplicating images in different tints or orientations, thereby…

Retrieval-Augmented Generation (RAG) has emerged as a prominent method for incorporating domain knowledge into Large Language Models (LLMs). While RAG enhances response relevance by incorporating retrieved domain knowledge in the context,…

Detecting anomalies has become an increasingly critical function in the financial service industry. Anomaly detection is frequently used in key compliance and risk functions such as financial crime detection fraud and cybersecurity. The…

Domain shift is a common problem in the realistic world, where training data and test data follow different data distributions. To deal with this problem, fully test-time adaptation (TTA) leverages the unlabeled data encountered during test…

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Recent advances in large language models (LLMs) have been driven by pretraining, supervised fine tuning (SFT), and alignment tuning. Among these, SFT plays a crucial role in transforming a model 's general knowledge into structured…

In this paper, we propose capturing and utilizing \textit{Temporal Information through Graph-based Embeddings and Representations} or \textbf{TIGER} to enhance multi-agent reinforcement learning (MARL). We explicitly model how inter-agent…

Incremental Learning is well known machine learning approach wherein the weights of the learned model are dynamically and gradually updated to generalize on new unseen data without forgetting the existing knowledge. Incremental learning…

[Context] Multi-agent reinforcement learning (MARL) has achieved notable success in environments where agents must learn coordinated behaviors. However, transferring knowledge across agents remains challenging in non-stationary environments…

Recent advances in data augmentation enable one to translate images by learning the mapping between a source domain and a target domain. Existing methods tend to learn the distributions by training a model on a variety of datasets, with…

The diversity of retinal imaging devices poses a significant challenge: domain shift, which leads to performance degradation when applying the deep learning models trained on one domain to new testing domains. In this paper, we propose a…

We investigate the boundary between chemotaxis driven by spatial estimation of gradients and chemotaxis driven by temporal estimation. While it is well known that spatial chemotaxis becomes disadvantageous for small organisms at high noise…

Conventional domain adaptation typically transfers knowledge from a source domain to a stationary target domain. However, in many real-world cases, target data usually emerge sequentially and have continuously evolving distributions.…

Evaluating the potential of a prospective candidate is a common task in multiple decision-making processes in different industries. We refer to a prospect as something or someone that could potentially produce positive results in a given…