2 papers
cs.LG2026
Forking: Sudden Overfitting Under Replay
Shanbin Yu, Shaoyang Guo, Haoran Zhao +2
This paper studies forking, a generalization failure discovered in NanoGPT autoresearch. Under data replay, models with an over-encoding n-gram memory branch show a sharp separatio…
cs.AI2026
ArchitectureIQ: On the Measure of Training Intuition
Zirui Ren, Shaoyang Guo, Chencheng Tang +9
Top researchers have good intuition, but do language models have as good intuition about model training as top AI researchers? To measure model intuition of LLMs and humans, we int…