Home  | News

14.10.2025

Teaser image to Industry Pitch Talks Recap

Industry Pitch Talks Recap

With the Munich NLP Community

On October 7th, we hosted another session in our “Pitchtalks with Industry” series — this time in collaboration with Munich NLP. The event brought together more than 50 members of Munich’s NLP community.

This edition featured:

  • Verena Blaschke (MCML PhD student in the group of our PI Barbara Plank), who walked us through the chaos of processing German dialects — from inconsistent spellings and data scarcity to tokenizers that break when faced with dialect words. Turns out, dialect NLP is way fuzzier and more complex than you might expect!
  • Evgeniya Sukhodolskaya from Qdrant introduced miniCOIL — an approach to make search understand meaning, not just match keywords. Think BM25, but with semantic understanding.

Thanks to everyone who joined and contributed to the discussions — and to our partners at Munich NLP for helping make this event such a success!

#event #research

Related

Link to Cybersecurity: “Even smart light bulbs harbor risks”

24.03.2026

Cybersecurity: “Even Smart Light Bulbs Harbor Risks”

Interview with computer science expert Johannes Kinder on digital security in everyday life.

Read more
Link to MCML Members Win Most Cited Article Award at ECR 2026

24.03.2026

MCML Members Win Most Cited Article Award at ECR 2026

MCML researchers win top citation award for ChatGPT radiology study, highlighting benefits and risks in patient communication.

Read more
Link to MCML at the Bay Area

20.03.2026

MCML at the Bay Area

MCML joined a Bavarian delegation to the Bay Area, engaging with leading AI organizations to foster collaboration and strengthen global research ties.

Read more
Link to MCML Reaches h-Index of 100

20.03.2026

MCML Reaches H-Index of 100

MCML reaches an h-index of 100, marking a milestone achieved through years of collaboration with LMU Munich, TUM, and research partners worldwide.

Read more
Link to Teaching Models to Say ‘I’m Not Sure’

19.03.2026

Teaching Models to Say ‘I’m Not Sure’

Unified diffusion theory for images and text, bridging continuous and discrete models in one clear framework for generative AI.

Read more
Back to Top