Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
When Data Imbalance Helps: Robust Generalization Through Shortcut Saturation
Cheng-Ting Chou, Duc Binh Hoang
We study robust generalization under spurious correlations: tasks where a shortcut feature is correlated with the true label in training but anti-correlated in an adversarial held-…
cs.LG2025
Universal Neurons in GPT-2: Emergence, Persistence, and Functional Impact
Advey Nandan, Cheng-Ting Chou, Amrit Kurakula +4
We investigate the phenomenon of neuron universality in independently trained GPT-2 Small models, examining these universal neurons-neurons with consistently correlated activations…