collaborators

5 papers

cs.CL2025

Optimizing Humor Generation in Large Language Models: Temperature Configurations and Architectural Trade-offs

Evgenii Evstafev

Large language models (LLMs) demonstrate increasing capabilities in creative text generation, yet systematic evaluations of their humor production remain underexplored. This study…

cs.LG2025

The Paradox of Stochasticity: Limited Creativity and Computational Decoupling in Temperature-Varied LLM Outputs of Structured Fictional Data

Evgenii Evstafev

This study examines how temperature settings and model architectures affect the generation of structured fictional data (names, birthdates) across three large language models (LLMs…

cs.LG2025

Token-Hungry, Yet Precise: DeepSeek R1 Highlights the Need for Multi-Step Reasoning Over Speed in MATH

Evgenii Evstafev

This study investigates the performance of the DeepSeek R1 language model on 30 challenging mathematical problems derived from the MATH dataset, problems that previously proved uns…

cs.LG2025

Token-by-Token Regeneration and Domain Biases: A Benchmark of LLMs on Advanced Mathematical Problem-Solving

Evgenii Evstafev

Large language models (LLMs) excel in many natural language tasks, yet they struggle with complex mathemat-ical problem-solving, particularly in symbolic reasoning and maintaining…

cs.CV2025

Benchmarking Multimodal Models for Fine-Grained Image Analysis: A Comparative Study Across Diverse Visual Features

Evgenii Evstafev

This article introduces a benchmark designed to evaluate the capabilities of multimodal models in analyzing and interpreting images. The benchmark focuses on seven key visual aspec…