Publications

Projects

  • Composable AI Pipelines Write intent, not infrastructure
  • Infinite Interfaces Do design principles ever really change?
  • GUIrilla Automated desktop UI exploration
  • MacArena Agents fight it out on real macOS
  • SwiftEval Benchmarking code LLMs in Swift
  • Neural Engine Inference LLM inference on the Apple Neural Engine
  • GenRA LLM-driven animation of rigged 3D models

More from Research

All projects Publications Partnership People
Partnership People
MacPaw AI MacPaw
Publications Projects Partnership People
MacPaw AI MacPaw
← All people
Yana Kurliak

Yana Kurliak

AI & Research Scientist

  • Google Scholar
  • LinkedIn

Publications

Artificial Intelligence | FORGE 2025 The 2nd ACM International Conference on AI Foundation Models and Software Engineering

SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation

Ivan Petrukha, Yana Kurliak and Nataliia Stulova

Read paper
Making tech your friend

Research

  • Publications
  • Composable AI Pipelines
  • Infinite Interfaces
  • GUIrilla
  • MacArena
  • SwiftEval
  • Neural Engine Inference
  • GenRA
  • Partnership
  • People

Resources

  • Open source
  • Models on Hugging Face
  • RSS feed

Company

  • MacPaw AI
  • macpaw.com

Contact

  • ai@macpaw.com
  • GitHub
  • Hugging Face
  • X
  • LinkedIn

Apple, Mac, macOS, iOS, Swift, SwiftUI, Metal, and Spotlight are trademarks of Apple Inc., registered in the U.S. and other countries and regions. Claude is a trademark of Anthropic, PBC; OpenAI and GPT are trademarks of OpenAI. All other product names, logos, and brands are the property of their respective owners and are used for identification purposes only; their use does not imply endorsement. MacPaw Research is a research department at MacPaw and is not affiliated with or endorsed by Apple Inc., OpenAI, Anthropic, or any other trademark holder.

© 2026 MacPaw Way Ltd. Kyiv-born PrivacyCookie PolicyTerms