What a model learns depends on what it is trained on, and in what order. These conversations look at pretraining dynamics, how training data shapes model abilities, data mixtures and scaling laws, and when domain data belongs in pretraining rather than fine-tuning.
4 conference interviews
From conferences and workshops

COLM 2026 · October 21, 2026 · 8 min
Kimia Hamidieh, MIT

COLM 2026 · October 19, 2026 · 7 min
Chandreyi (Zini) Chakraborty, Georgia Tech

COLM 2026 · October 7, 2026 · 23 min
Christina Baek, Carnegie Mellon University / DatologyAI

COLM 2026 · October 5, 2026 · 32 min
Emmy Liu, Carnegie Mellon University