Read more
This two-volume set, LNAI 16301 and LNAI 16302, constitutes the refereed proceedings of the 45th SGAI International Conference on Artificial Intelligence, AI 2025, held in Cambridge, UK, during December 16-18, 2025.
The 47 full papers and 20 short papers presented in these two volumes were carefully reviewed and selected from 93 submissions. The papers are grouped into these topical sections:
Part I: Technical Papers; Deep Learning; Large Language Models; Machine Learning; Neural Networks;
Techniques of AI and Short Technical Papers.
Part II: Application Papers; Evolutionary Algorithms; Machine Learning; Neural Networks; Medical Computing and Health Informatics; Large Language Models; Natural Language Processing and Machine Vision; Applications of Artificial Intelligence and Short Application Papers.
List of contents
.- Technical Papers.
.- DESS: Dimensional-PDFs for Embedding Space Sampling (Best Technical Paper.
.- Deep Learning.
.- A Hybrid Reasoning System for Visual Arithmetic Learning.
.- NERULA: A Dual-Pathway Self-Supervised Learning Framework for Electrocardiogram Signal Analysis.
.- This Looks Like That and That and That: Multi-objective Optimization for Diverse Prototype Learning.
.- Large Language Models.
.- Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking.
.- Data and Knowledge-Driven Approach for Energy Profiling in Smart Context-Aware Buildings.
.- Retry and Refine: A Multi-Agent Framework for LLM Based Reliable Unit Test Generation.
.- English K_Quantization of LLMs Does Not Disproportionately Diminish Multilingual Performance.
.- Rethinking the Illusion of Thinking.
.- TravQuery: A Customer Support Chatbot based on Retrieval Augmented Generation (RAG).
.- Machine Learning.
.- 6D Grasp Pose Estimation using Machine Learning with Synthetic Data: Explainable Grasping with Point Cloud Networks.
.- A New Longitudinal Classification Method Based on Stacking Predictions for Separate Time Points.
.- Measuring and Comparison of the Energy Consumption of different Machine Learning Methods.
.- Machine Learning-Enhanced Production Frontier Estimation: An EATBoosting Variant.
.- A Comparative Study of Feature Selection in Tsetlin Machines.
.- MTL-LungNet: A Unified Model for Nodule Segmentation and Malignancy Classification.
.- Neural Networks.
.- Two-Stage Graph Convolutional Framework for Pipeline Leak Detection and Size Identification.
.- TamilSandhi: A Neuro-Symbolic AI toolkit for correcting Sandhi errors in Tamil.
.- Techniques of AI.
.- Navigating the N-Person Prisoners` Dilemma: From the Tragic Valley to the Collaborative Hill.
.- Evolutionary Harnessing of Sneak Currents of 1R Memristive Crossbar.
.- Short Technical Papers.
.- Bias Detection in Online Higher Education Texts: Comparing Fine-Tuned and Zero-Shot LLM Approaches.
.- Enhancing Deepfake Detection with Audio Spectrograms and Siamese Networks.
.- Learning to Navigate and Track: A Decentralized RL Framework for UAV Operations in GNSS-Denied Terrain.
.- Dynamic Fusion of Structured Covariates into Deep Signal Backbones.
.- Global Explanations for Imitation Learning.
.- Attention or Convolution? Comparing Modern Architectures for Stress Detection on BVP Image Encodings.
.- High-Confidence Clustering and Lightweight U-Net for SAR Change Detection.
.- Towards a Technical Definition of Artificial Intelligence and Machine Learning Software Systems.
