Results 61 to 70 of about 776 (171)
Tibetan Few‐Shot Learning Model With Deep Contextualised Two‐Level Word Embeddings
CAAI Transactions on Intelligence Technology, Volume 10, Issue 5, Page 1394-1410, October 2025.ABSTRACT Few‐shot learning is the task of identifying new text categories from a limited set of training examples. The two key challenges in few‐shot learning are insufficient understanding of new samples and imperfect modelling. The uniqueness of low‐resource languages lies in their limited linguistic resources, which directly leads to the difficulty ...
Ziyue Zhang +11 more
wiley +1 more source
BotOrNot: A Platform for Conducting Experiments with Undisclosed Chat Agents
, 2022 Chatbots are omnipresent in today's online environments in work and private life. While early chatbots were easy to identify, recently released open-domain chatbots, such as GPT3 and Blenderbot2, increasingly blur the line between human and chatbot ...
Maedche, Alexander +2 more
core +1 more source
The Rise of Large Language Models: Evolution, Applications, and Future Directions
Engineering Reports, Volume 7, Issue 9, September 2025.This paper provides a comprehensive Systematic Literature Review (SLR) on Large Language Models (LLMs), covering their evolution, applications, evaluation metrics, and challenges. It identifies key research gaps and future directions, offering a structured taxonomy and analysis of performance environments, datasets, and open issues in LLM research ...
Amir Masoud Rahmani +2 more
wiley +1 more source
Geodesy and GeodynamicsThe precise correction of atmospheric zenith tropospheric delay (ZTD) is significant for the Global Navigation Satellite System (GNSS) performance regarding positioning accuracy and convergence time.
Debao Yuan +6 more
doaj +1 more source
ML@ChemE: Past, Present, and Future of Machine Learning in Chemical Engineering
ChemBioEng Reviews, Volume 12, Issue 4, August 2025.Although the initial machine learning (ML) applications were mainly on fault detection, signal processing, and process modeling, they extended to new areas like property estimation and material screening in later years; energy technologies, environmental issues, health, and new materials will likely be more important in future with the use of larger ...
Pınar Özdemir, Ramazan Yıldırım
wiley +1 more source
Regional Tropospheric Delay Prediction Model Based on LSTM-Enhanced Encoder Network
IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingPrecise modeling of zenith tropospheric delay (ZTD) is essential for real-time high-precision positioning in global navigation satellite systems. Due to the stochastic variability of atmospheric water vapor across different regions, tropospheric delay ...
Yuanfang Peng +5 more
doaj +1 more source
Optimizing PPP Performance by Incorporating ZWD Constraints Derived From Data Assimilation
Earth and Space Science, Volume 12, Issue 8, August 2025.Abstract One of the primary error sources limiting the performance of the Precise Point Positioning (PPP) technique is the atmospheric wet delay, caused by the presence of water vapor in the lower atmosphere. Accurately representing this parameter is crucial for improving the initialization and accuracy of satellite‐based positioning techniques ...
Masoud Dehvari +2 more
wiley +1 more source
Artificial Intelligence on Campus: Revisiting Understanding as an Aim of Higher Education
Educational Theory, Volume 75, Issue 4, Page 603-625, August 2025.Abstract The launch of the powerful generative AI tool ChatGPT in November 2022 sparked a wave of fear across higher education. The tool could seemingly be used to write essays and do other work without students putting in the effort expected of them. In this paper, Jamie Herman and Henry Lara‐Steidel posit a way of addressing the concerns over ChatGPT
Jamie Herman, Henry Lara‐Steidel
wiley +1 more source
ChatGPT's Performance Evaluation in Spreadsheets Modelling to Inform Assessments Redesign
Journal of Computer Assisted Learning, Volume 41, Issue 3, June 2025.ABSTRACT Background Increasingly, students are using ChatGPT to assist them in learning and even completing their assessments, raising concerns of academic integrity and loss of critical thinking skills. Many articles suggested educators redesign assessments that are more ‘Generative‐AI‐resistant’ and to focus on assessing students on higher order ...
Michelle Cheong
wiley +1 more source
ESPACE: Dimensionality Reduction of Activations for Model Compression [PDF]
We propose ESPACE, an LLM compression technique based on dimensionality reduction of activations. Unlike prior works on weight-centric tensor decomposition, ESPACE projects activations onto a pre-calibrated set of principal components.
Khailany, Brucek, Sakr, Charbel
core +1 more source