PyData Warsaw #32 - Piotr Siciński & Serhii Sokolenko

18:00 - Piotr Siciński - Carnegie Mellon University / WUT - "Heart Rate from Video: Techniques and Challenges"
About topic: Remote photoplethysmography (rPPG) estimates heart rate from ordinary video by analyzing subtle, pulse-driven color changes in the skin. It enables contactless physiological monitoring in situations where wearables or medical sensors are impractical, such as outdoor screening, emergency response, and camera-based systems. While rPPG performs well in controlled indoor settings, outdoor use is limited by changing illumination, motion, and occlusions that distort the signal. Real-world datasets illustrate how these environmental factors impact rPPG performance under natural conditions. Time-series–focused AI models offer a promising way forward by emphasizing temporal structure and robustness to noisy, degraded signals. The talk will cover current state of the domain as well as recent advancements and research directions.
About speaker: Piotr Siciński is a master’s student in Computer Science at Warsaw University of Technology. His research and professional interests focus on applied artificial intelligence. He has interned as a summer scholar at Carnegie Mellon University and as a software engineer at Google, where he worked on AI-related projects. Previously, he worked on medical sensors R&D at Tricholab.

18:45 - Serhii Sokolenko - Tower - "Surviving the Agentic Hype with Small Language Models"
About topic: The AI landscape is abuzz with talk of "agentic intelligence" and "autonomous reasoning." But beneath the hype, a quieter revolution is underway: Small Language Models (SLMs) are starting to perform the core reasoning and orchestration tasks once thought to require massive LLMs. In this talk, we’ll demystify the current state of “AI agents,” show how compact models like Phi-2, xLAM 8B, and Nemotron-H 9B can plan, reason, and call tools effectively, and demonstrate how you can deploy them on consumer-grade hardware. Using Python and lightweight frameworks such as LangChain, we’ll show how anyone can quickly build and experiment with their own local agentic systems. Attendees will leave with a grounded understanding of agent architectures, SLM capabilities, and a roadmap for running useful agents without the GPU farm.
About speaker: Serhii Sokolenko is a co-founder of Tower.dev. Prior to founding Tower, Serhii worked at Databricks, Snowflake and Google on data processing and databases.

After the event, together with our sponsor Tower, we will invite you for pizza!
About sponsor: Tower is where engineers ship data flows faster. Tower provides analytical compute and storage to data platform builders, including Pythonic and Agentic orchestration of flows and a managed Iceberg lakehouse.

Venue:
Centrum Innowacji Politechniki Warszawskiej, ul. Rektorska 4
Room 3.12 (3rd Floor)