Related papers: Train-On-Request: An On-Device Continual Learning …
The ability of deep neural networks to continually learn and adapt to a sequence of tasks has remained challenging due to catastrophic forgetting of previously learned tasks. Humans, on the other hand, have a remarkable ability to acquire,…
Fault detection is essential in complex industrial systems to prevent failures and optimize performance by distinguishing abnormal from normal operating conditions. With the growing availability of condition monitoring data, data-driven…
Deep Learning (DL) has transformed the automation of a wide range of industries and finds increasing ubiquity in society. The high complexity of DL models and its widespread adoption has led to global energy consumption doubling every 3-4…
Sample efficiency remains a major obstacle for real world adoption of reinforcement learning (RL): success has been limited to settings where simulators provide access to essentially unlimited environment interactions, which in reality are…
The prevalence of online learning poses a vital challenge in real-time monitoring of students' concentration. Traditional methods such as questionnaire assessments require manual intervention, and webcam-based monitoring fails to provide…
Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined with parameter-efficient fine-tuning (PEFT) have shown…
This paper presents a control interface to translate the residual body motions of individuals living with severe disabilities, into control commands for body-machine interaction. A custom, wireless, wearable multi-sensor network is used to…
As the pursuit of synergy between Artificial Intelligence (AI) and Operations Research (OR) gains momentum in handling complex inventory systems, a critical challenge persists: how to effectively reconcile AI's adaptive perception with OR's…
We develop a novel multi-objective reinforcement learning (MORL) framework to jointly optimize wireless network selection and autonomous driving policies in a multi-band vehicular network operating on conventional sub-6GHz spectrum and…
Background: Upper-limb weakness and tremor (4--12 Hz) limit activities of daily living (ADL) and reduce adherence to home rehabilitation. Objective: To assess technical feasibility and clinician-relevant signals of a sensor-fused wearable…
Purpose: Surgery scene understanding with tool-tissue interaction recognition and automatic report generation can play an important role in intra-operative guidance, decision-making and postoperative analysis in robotic surgery. However,…
Adaptive Virtual Reality (VR) systems have the potential to enhance training and learning experiences by dynamically responding to users' cognitive states. This research investigates how eye tracking and heart rate variability (HRV) can be…
Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data selection critical for training efficiency. Existing methods derive selection signals…
Offline Reinforcement Learning (RL) is structured to derive policies from static trajectory data without requiring real-time environment interactions. Recent studies have shown the feasibility of framing offline RL as a sequence modeling…
In the context of Brain-Computer Interfaces, we propose an adaptive method that reaches offline performance level while being usable online without requiring supervision. Interestingly, our method does not require retraining the model, as…
Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on previously learned tasks. This setting corresponds to domains where new tasks arise over…
The question of how cyber-physical systems should interact with human partners that can take over control or exert oversight is becoming more pressing, as these systems are deployed for an ever larger range of tasks. Drawing on the…
Compared to overlay-based tensor architectures like VTA or Gemmini, compilers that directly translate machine learning models into a dataflow architecture as HLS code, such as HLS4ML and FINN, generally can achieve lower latency by…
Machine learning on electromyography (EMG) has recently achieved remarkable success on a variety of tasks, while such success relies heavily on the assumption that the training and future data must be of the same data distribution. However,…
Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the actor policy based on…