AI Meetup February 2026

Agenda
18:00 – 18:10; Reception
18:10 – 18:15; A welcome note from Organiser & host/sponsor

18:15 - 18:45; Speaker I: Daniel Fitzpatrick
Title: Do you have an ice-cold beer for me?
Description: In this session, I will introduce Pragmatic Metacognitive Prompting (PMP) as a novel approach to improve sarcasm detection in Large Language Models (LLMs). PMP leverages pragmatic reasoning and metacognitive strategies to enhance the interpretation of implied meanings and contextual cues, achieving improved performance on sarcasm detection benchmarks.
Why is this session innovative and interesting for your future participants?
This entertaining, interactive, session is innovative because it integrates pragmatic theories into LLM prompting, offering a new direction for sentiment analysis research. It stands out by demonstrating how linguistic principles – such as implicature – influence human reasoning in complex emotional contexts, enhancing sarcasm detection capabilities.
Who is your audience and what are the key takeaways for them?
The target audience includes AI researchers, NLP practitioners, and data scientists interested in sentiment analysis and language model enhancement. Key takeaways include understanding the application of pragmatic theories in Natural Language Processing, insights into advanced sarcasm detection methods, and practical knowledge of implementing metacognitive prompting.

18:45 - 19:15; Speaker II: Xiaojing Zhao
Title: Agentic Commerce in the German Retail
Abstract: Agentic commerce refers to commerce scenarios where AI agents can independently handle tasks such as product discovery, comparison, purchasing, and follow-up actions within predefined rules and user consent. This talk introduces the concept through practical use cases and focuses on the specific characteristics of the German and European market: strong data protection and regulatory requirements, high expectations for transparency and trust, and cautious but structured adoption by retailers. We will contrast this with the more platform-driven development in the U.S. and the highly integrated, automation-first approach in China. The session will also introduce a Market Study Program currently under construction, and we warmly invite retailers to join the program to help shape how agentic commerce can work in a European context.

19:15 - 19:45; Break

19:45 - 20:15; Speaker III: Advait Baijulal, Madhuvanthi Venkatesh
Title: BERTifying Intelligence
Abstract: How much model complexity do we really need for high performing text classification? In this talk, young researcher Advait (who is just 17!) will present a comparative study of BERT, RoBERTa, DistilBERT, and TinyBERT trained on a shared dataset, evaluating accuracy, efficiency, and inference speed. The findings reveal the real trade offs between model size and scalability, highlighting how lighter architectures can deliver powerful, practical AI solutions.

20:15 - 20:20; Speaker IV: Andriy Goldmann

20:20 - 20:30; Announcements (Are you hiring, looking for a job, or seeking a co-founder or investor? Do you have something to share with the community? Use this space and stage)

20:30 - Socializing

Location: Harvard-Raum, Room No: S 0.01, Ground Floor, Frankfurt School of Finance and Management Main Campus.

Interested in speaking?
Link to our Speaker Form: Google Form

Interested in sponsoring?
Partner with us to support the AI community and gain visibility among industry professionals and enthusiasts.
Link to our Sponsorship Form: Google Form

Organizers:
Danko
Peter
Gautam
Frank
Madhu
AI Meet-up Linkedin Page: https://www.linkedin.com/company/ai-meetup-frankfurt/