This book constitutes the refereed proceedings of the 12th International Conference on , AIST 2024, held in Bishkek, Kyrgyzstan, during October 17–19, 2024.
The 16 full papers included in this book were carefully reviewed and selected from 70 submissions. They were organized in topical sections as follows: Natural Language Processing; Computer Vision; Data Analysis and Machine Learning; and Theoretical Machine Learning and Optimization.
.- Keynote and Invited Papers.
.- KyrgyzNLP: Challenges, Progress, and Future.
.- Modeling Information Influence and Control in Social Networks: Integrating
Opinions, Trust, Reputation, and Agent Dynamics.
.- Natural Language Processing.
.- Graphical Abbreviation Disclosure in Russian Language.
.- Iterative Improvement of an Additively Regularized Topic Model.
.- Key Algorithms for Keyphrase Generation: Instruction-Based LLMs
for Russian Scientific Keyphrases.
.- Shrink the longest: improving latent space isotropy with
simplicial geometry.
.- Redefining Annotation Practices: Leveraging Large Language Models for
Discourse Annotation.
.- GERA: a corpus of Russian school texts annotated for Grammatical Error
Correction.
.- From Tokens to Tales: Semantic Similarity in Story Generation.
.- Cross-Language Summarization in Russian and Chinese Using
the Reinforcement Learning.
.- Computer Vision.
.- Temporal Modeling via TCN and Transformer for Audio-Visual Emotion
Recognition.
.- YOLO-HTR: Page-Level Recognition of Historical Handwritten Document
Collections.
.- Data Analysis and Machine Learning.
.- An optimal set of implications in triadic contexts.
.- Uniting contrastive and generative learning for event sequences models.
.- Theoretical Machine Learning and Optimization.
.- An asymptotically optimal algorithm for the minimum weight spanning tree
with arbitrarily bounded diameter on random inputs.
.- Automatic Adaptive Conformal Inference for Time Series Forecasting.
