Emergent Capabilities in Modern Sequence Models: Phase Transitions, Memory in Shallow Transformers, and Bidirectional State-Space Architectures.

Thumbnail

Event details

Date 17.06.2025
Hour 14:0016:00
Speaker Fabrizio Boncoraglio
Location
Category Conferences - Seminars
EDIC candidacy exam
Exam president: Prof. Michael Gastpar
Thesis advisor: Prof. Lenka Zdeborova
Co-examiner: Prof. Matthieu Wyart

Abstract
coming soon

Selected papers
- A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention: https://arxiv.org/pdf/2402.03902
- Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers: https://arxiv.org/pdf/2407.09941
- Understanding Factual Recall in Transformers via Associative Memories: https://arxiv.org/pdf/2412.06538 

Practical information

  • General public
  • Free

Contact

  • edic@epfl.ch

Tags

EDIC candidacy exam

Share