相关论文: HERA-B Framework for Online Calibration and Alignm…
While test-time scaling has enabled large language models to solve highly difficult tasks, state-of-the-art results come at exorbitant compute costs. These inefficiencies can be attributed to the miscalibration of post-trained language…
Modern Transformer-based models frequently suffer from miscalibration, producing overconfident predictions that do not reflect true empirical frequencies. This work investigates the calibration dynamics of LoRA: Low-Rank Adaptation and a…
Environment perception is a key component of any autonomous system and is often based on a heterogeneous set of sensors and fusion thereof for which sensor sensor calibration plays fundamental role. It can be divided to intrinsic and…
AI is poised to revolutionize telecommunication networks by boosting efficiency, automation, and decision-making. However, the black-box nature of most AI models introduces substantial risk, possibly deterring adoption by network operators.…
In recent years, functional linear models have attracted growing attention in statistics and machine learning, with the aim of recovering the slope function or its functional predictor. This paper considers online regularized learning…
Conformance checking techniques aim to collate observed process behavior with normative/modeled process models. The majority of existing approaches focuses on completed process executions, i.e., offline conformance checking. Recently, novel…
Accurate uncertainty estimates are important in sequential model-based decision-making tasks such as Bayesian optimization. However, these estimates can be imperfect if the data violates assumptions made by the model (e.g., Gaussianity).…
In 2015, the LHCb experiment established a new and unique software trigger strategy with the purpose of increasing the purity of the signal events by applying the same algorithms online and offline. To achieve this, real-time calibration…
Neural networks solving real-world problems are often required not only to make accurate predictions but also to provide a confidence level in the forecast. The calibration of a model indicates how close the estimated confidence is to the…
Complex robot behaviour typically requires the integration of multiple robotic and Artificial Intelligence (AI) techniques and components. Integrating such disparate components into a coherent system, while also ensuring global properties…
A fast, efficient and comprehensive monitoring system is a vital part of any HEP experiment. This paper describes the software framework that will be used during ATLAS data taking to monitor the state of the data acquisition and the quality…
Artificial intelligence and deep learning are currently reshaping numerical simulation frameworks by introducing new modeling capabilities. These frameworks are extensively investigated in the context of model correction and…
A machine learning model is calibrated if its predicted probability for an outcome matches the observed frequency for that outcome conditional on the model prediction. This property has become increasingly important as the impact of machine…
High fidelity estimation algorithms for robotics require accurate data. However, timestamping of sensor data is a key issue that rarely receives the attention it deserves. Inaccurate timestamping can be compensated for in post-processing…
Large language model alignment is widely used and studied to avoid LLM producing unhelpful and harmful responses. However, the lengthy training process and predefined preference bias hinder adaptation to online diverse human preferences. To…
Retrieval-augmented generation (RAG) systems often rely on static retrieval, limiting adaptation to evolving intent and content drift. We introduce Dynamic Memory Alignment (DMA), an online learning framework that systematically…
Modern high-energy physics experiments collect data using dedicated complex multi-level trigger systems which perform an online selection of potentially interesting events. In general, this selection suffers from inefficiencies. A further…
Accurate sensor calibration is crucial for autonomous systems, yet its uncertainty quantification remains underexplored. We present the first approach to integrate uncertainty awareness into online extrinsic calibration, combining Monte…
An adaptive observer is designed for online estimation of Hilbert-Schmidt operators from online measurement of the state for some class of nonlinear infinite-dimensional dynamical systems. Convergence is ensured under detectability and…
Many real-world brain-computer interface (BCI) applications rely on single-trial classification of event-related potentials (ERPs) in EEG signals. However, because different subjects have different neural responses to even the same…