Noa Yehezkel Lubin

To Predict or To Generate? That Is the Question
Noa Lubin

Abstract

Large language models (LLMs) are transforming textual documents classification, parsing and verification, but how do they compare to traditional tools like AWS textract and rule-based systems? In this roundtable, we’ll explore when LLMs outperform existing methods, where OCR and deterministic rules remain essential, and how to balance accuracy, speed, and cost. Join the discussion to share experiences, challenges, and strategies for integrating GenAI document pipelines while cutting through the hype to uncover its real impact.

Bio

Noa is the Director of Data & AI at Fido and is interested in any do-good AI. She loves public speaking and teaching data science and is a part of Y-data and DART faculty. Noa previously worked at: Diagnostic Robotics, NASA, Amazon, Elbit, and IAI. She completed a computer science master’s degree at Bar-Ilan University with an NLP thesis and an electrical engineering bachelor’s degree at the Technion. She is also the proud author of a children’s book about AI.

Agenda

8:45 Reception
9:30 Opening remarks by WiDS TLV ambassadors
9:45 Dr. Mor Geva , Tel Aviv University: “MRI for Large Language Models: Mechanistic Interpretability from Neurons to Attention Heads”
10:15 Panel: “Pioneering Progress: a strategic look at the GenAI revolution and the new role of data scientists“
Shani Gershtein, Melingo
Mirit Elyada Bar, Intuit
Dr. Asi Messica, Lightricks
Moderated by Nitzan Gado, Intuit
10:45 Poster pitches
10:55 Break
11:10 Lightning talks session
12:30 Lunch & poster session
13:30 Roundtable session & poster session
14:30 Roundtable closing
14:40 Shunit Agmon, Technion: “Bridging the Gender Gap in Clinical AI: Temporal Adaptation with TeDi-BERT”
15:00 Shaked Naor Hoffmann, Apartment List: “Building Generative AI Agents for Production: Turning Ideas into Real-World Applications”
15:20 Closing remarks
15:30 The end