Related papers: AI-based automated active learning for discovery o…
Understanding and extracting structured insights from unstructured documents remains a foundational challenge in industrial NLP. While Large Language Models (LLMs) enable zero-shot extraction, traditional pipelines often fail to handle…
Recent advancements in multimodal foundation models (e.g., CLIP) have excelled in zero-shot generalization. Prompt tuning involved in the knowledge transfer from foundation models to downstream tasks has gained significant attention…
Activity recognition from long unstructured egocentric photo-streams has several applications in assistive technology such as health monitoring and frailty detection, just to name a few. However, one of its main technical challenges is to…
Recent 2D-to-3D human pose estimation (HPE) utilizes temporal consistency across sequences to alleviate the depth ambiguity problem but ignore the action related prior knowledge hidden in the pose sequence. In this paper, we propose a…
Autonomous vehicles demand high accuracy and robustness of perception algorithms. To develop efficient and scalable perception algorithms, the maximum information should be extracted from the available sensor data. In this work, we present…
Autonomous experimentation (AE) combines machine learning and research hardware automation in a closed loop, guiding subsequent experiments toward user goals. As applied to materials research, AE can accelerate materials exploration,…
Control applications often feature tasks with similar, but not identical, dynamics. We introduce the Hidden Parameter Markov Decision Process (HiP-MDP), a framework that parametrizes a family of related dynamical systems with a…
In this paper, we give a new approximate dynamic programming (ADP) method to solve large-scale Markov decision programming (MDP) problem. In comparison with many classic ADP methods which have large number of constraints, we formulate an…
Many real-life decision-making situations allow further relevant information to be acquired at a specific cost, for example, in assessing the health status of a patient we may decide to take additional measurements such as diagnostic tests…
Active Feature Acquisition is an instance-wise, sequential decision making problem. The aim is to dynamically select which feature to measure based on current observations, independently for each test instance. Common approaches either use…
Sampling from flat modes in discrete spaces is a crucial yet underexplored problem. Flat modes represent robust solutions and have broad applications in combinatorial optimization and discrete generative modeling. However, existing sampling…
In this work, we study dynamic programming (DP) algorithms for partially observable Markov decision processes with jointly continuous and discrete state-spaces. We consider a class of stochastic systems which have coupled discrete and…
Electroencephalography (EEG) during sleep is used by clinicians to evaluate various neurological disorders. In sleep medicine, it is relevant to detect macro-events (> 10s) such as sleep stages, and micro-events (<2s) such as spindles and…
We investigate active learning in the context of deep neural network models for change detection and map updating. Active learning is a natural choice for a number of remote sensing tasks, including the detection of local surface changes:…
We present a new deep learning-based machine learning potential (MLP) for molecular dynamics simulations of solid carbon monoxide (CO), capable of accurately describing CO vibrations both in the fundamental state and in highly excited…
Single-beam scanning electron microscopes (SEM) are widely used to acquire massive data sets for biomedical study, material analysis, and fabrication inspection. Datasets are typically acquired with uniform acquisition: applying the…
Detecting early warning indicators for abrupt dynamical transitions in complex systems or high-dimensional observation data is essential in many real-world applications, such as brain diseases, natural disasters, and engineering…
Learning interpretable representations of neural dynamics at a population level is a crucial first step to understanding how observed neural activity relates to perception and behavior. Models of neural dynamics often focus on either…
Active Learning (AL) aims to enhance the performance of deep models by selecting the most informative samples for annotation from a pool of unlabeled data. Despite impressive performance in closed-set settings, most AL methods fail in…
While the identification of nonlinear dynamical systems is a fundamental building block of model-based reinforcement learning and feedback control, its sample complexity is only understood for systems that either have discrete states and…