6 papers
Adaptive Soft Rolling KV Freeze with Entropy-Guided Recovery: Sublinear Memory Growth for Efficient LLM Inference
Adilet Metinov, Gulida M. Kudakeeva, Bolotbek uulu Nursultan +1
We present Adaptive Soft Rolling KV Freeze with Entropy-Guided Recovery (ASR-KF-EGR), a training-free inference-time framework for efficient large language model generation. Our me…
Theoretical Foundations of GPU-Native Compilation for Rapid Code Iteration
Adilet Metinov, Gulida M. Kudakeeva, Gulnara D. Kabaeva
Current AI code generation systems suffer from significant latency bottlenecks due to CPU-GPU data transfers during compilation, execution, and testing phases. We establish theoret…
KyrgyzBERT: A Compact, Efficient Language Model for Kyrgyz NLP
Adilet Metinov, Gulida M. Kudakeeva, Gulnara D. Kabaeva
Kyrgyz remains a low-resource language with limited foundational NLP tools. To address this gap, we introduce KyrgyzBERT, the first publicly available monolingual BERT-based langua…
Human-Annotated NER Dataset for the Kyrgyz Language
Timur Turatali, Anton Alekseev, Gulira Jumalieva +2
We introduce KyrgyzNER, the first manually annotated named entity recognition dataset for the Kyrgyz language. Comprising 1,499 news articles from the 24.KG news portal, the datase…
Syntactic Transfer to Kyrgyz Using the Treebank Translation Method
Anton Alekseev, Alina Tillabaeva, Gulnara Dzh. Kabaeva +1
The Kyrgyz language, as a low-resource language, requires significant effort to create high-quality syntactic corpora. This study proposes an approach to simplify the development p…
HJ-Ky-0.1: an Evaluation Dataset for Kyrgyz Word Embeddings
Anton Alekseev, Gulnara Kabaeva
One of the key tasks in modern applied computational linguistics is constructing word vector representations (word embeddings), which are widely used to address natural language pr…