| Page 107 | Kisaco Research
Pharma and Biotech Patent Litigation USA - 2025 Skeleton Agenda

Beyond Benchmarks to Real Products:
Automatically convert trained AI models into optimized mobile apps, ready to deploy within hours—no app development required.

End-to-End Automated Pipeline:
Seamlessly perform AI model conversion, device-specific optimization (NPU/GPU/CPU), and automatic SDK and app template generation (Android, iOS, Flutter).

Real-World Impact & Use Cases:
Proven deployments across industries including healthcare and enterprise, delivering immediate value through reduced costs, enhanced data security, and superior real-time performance.

Author:

Yeonseok Kim

CEO
Zetic

Yeonseok Kim

CEO
Zetic

Following the MLCommons Q3 MLPerf Inference results announcement on the morning of Tuesday 9th September on the keynote stage, MLCommons Founder & Executive Director David Kantar will deliver a detailed analysis of the results followed by a Q&A session from the audience. 

Author:

Miro Hodak

Senior Member of Technical Staff, AI Performance Engineering
AMD

Miro Hodak is a Principal Member of Technical Staff at AMD, where he focuses on AI performance and benchmarking. Prior to joining AMD, he served as an AI Architect at Lenovo and was a professor in physics at North Carolina State University before that. 

Miro has been actively involved with MLPerf and MLCommons since 2020, contributing to the development of multiple MLPerf benchmarks and submitting results across several rounds of Inference and Training. Since 2023, he has served as co-chair of the MLPerf Inference Working Group.

He has authored peer-reviewed publications in fields ranging from artificial intelligence and computer science to materials science, physics, and biochemistry, with his work cited over 2,500 times.

Miro Hodak

Senior Member of Technical Staff, AI Performance Engineering
AMD

Miro Hodak is a Principal Member of Technical Staff at AMD, where he focuses on AI performance and benchmarking. Prior to joining AMD, he served as an AI Architect at Lenovo and was a professor in physics at North Carolina State University before that. 

Miro has been actively involved with MLPerf and MLCommons since 2020, contributing to the development of multiple MLPerf benchmarks and submitting results across several rounds of Inference and Training. Since 2023, he has served as co-chair of the MLPerf Inference Working Group.

He has authored peer-reviewed publications in fields ranging from artificial intelligence and computer science to materials science, physics, and biochemistry, with his work cited over 2,500 times.

Large language models can now power capable software agents, yet real‑world success comes from disciplined engineering rather than flashy frameworks. Most reliable agents are built from simple, composable patterns instead of heavy abstractions.


The talk will introduce patterns to add complexity and autonomy only when it pays off. Attendees should leave with a practical decision framework for escalating from a single prompt to multi‑step agents, also keeping in mind guardrails for shipping trustworthy, cost‑effective agents at scale. 

Author:

Sushant Mehta

Research Engineer
Google Deepmind

Sushant Mehta

Research Engineer
Google Deepmind