3 papers
cs.LG2025
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…
cs.DC2025
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…
cs.CL2025
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…