Curriculum learning changes the data. Progressive stacking changes the model. Human development changes both at once.
What happens when language model pretraining does the same?
We explore this in Curriculum-Guided Layer Scaling (CGLS) 🧵
First night back from international travel (to Korea with a 16-hour time difference), and my resting heart rate dropped by 22bpm… crazy. And here I thought I’d handled the jet-lag perfectly this time.
We keep saying LLMs "hallucinate." But what does that actually mean?
In our new position paper, we argue hallucination isn't just "wrong facts." It's inaccurate internal world modeling.
We formalize this precisely in a unified definition to appear at #ICML2026 (@icmlconf)👇