Eduard Zelenay

Mr. Eduard Zelenay

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 August 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MLMartin Lukac
Martin Lukac
Frantisek DuchonFrantisek Duchon
Frantisek Duchon
Jakub IvanJakub Ivan
Jakub Ivan
MDmartin dekan
martin dekan
EZEduard Zelenay
Eduard Zelenay
RPRadoslav Pšenka
Radoslav Pšenka
This paper presents a unified technical survey of Large Language Models (LLMs), connecting three layers of the modelling pipeline that existing surveys address in isolation: internal architecture, distributed training optimisation, and downstream adaptation. Its organising principle is the dependency between these layers—how a choice at one constrains what remains feasible at the next. The survey examines fundamental mechanisms (tokenisation, scaled dot-product attention, activation functions, and normalisation, including RMSNorm and pre- versus post-normalisation placement), then the engineering of training at scale: data, tensor, and pipeline parallelism, hybrid schemes, mixed-precision training with BF16 and FP8, ZeRO-Offload memory management, activation checkpointing, and compute-optimal scaling laws together with the conditions under which they fail. The adaptation section covers supervised and instruction fine-tuning, a comparison of parameter-efficient methods (LoRA, QLoRA, adapters, prefix and prompt tuning), Reinforcement Learning from Human Feedback with its reward-hacking failure mode, alternatives including DPO, KTO and Constitutional AI, Retrieval-Augmented Generation beyond the basic pipeline, and decoding strategies. Practical configuration guidance is given for 7B, 70B and trillion-parameter regimes. Dedicated treatments of Mixture-of-Experts architectures, long-context modelling, and hardware-aware co-design close the survey, with open challenges classified by origin and severity.

21 September 2026 in International Journal of Intelligent Robotics and Applications
Verified
Journal Article
Open access
PDF file
EZEduard Zelenay
Eduard Zelenay
MKMaroš Kocúr
Maroš Kocúr
MLMartin Lukac
Martin Lukac
Frantisek DuchonFrantisek Duchon
Frantisek Duchon
RMRastislav Marko
Rastislav Marko
Large Language Models (LLMs) have emerged as powerful tools for enabling intuitive human-robot interaction through natural language. However, existing approaches often lack evaluated voice control in languages other than English, integrated vision, and comprehensive safety mechanisms. We present SMaRTAban (Smart Multi-legged Robotic Transformer Agent Artaban), a system that combines a LangGraph ReAct agent with the quadruped mobile robot Artaban for natural language control. Our system integrates: (1) voice commands with automatic language detection via Whisper, evaluated on English and Slovak, (2) on-demand scene interpretation via GPT-4o vision, (3) a safety-focused system prompt with interruptible tool execution, and (4) a React-based GUI for transparent operation monitoring. A pilot voice-control evaluation on 120 samples showed robust semantic understanding across English and Slovak (BERTScore F1: 0.87–1.00), despite transcription challenges in Slovak. We further conducted 4,800 accepted tool-calling trials across two models, six agent and prompting configurations, two languages, and 10 command scenarios. The strongest configuration combined iterative ReAct execution, an explicit system prompt, and few-shot prompting with three task-specific movement examples, achieving a tool-call F1 of 0.9977 and 96.5% exact-sequence success with GPT-4o. A separate performance evaluation showed that remote transcription and model processing dominated response time, whereas local ROS communication contributed only a few milliseconds.