2 papers
cs.LG2026
When Do Graph Foundation Models Transfer? A Data-Centric Theory
Jiajun Zhu, Ying Chen, Peihao Wang +4
Graph foundation models (GFMs) aim to reuse a single backbone across diverse graph domains, yet their transfer is often uneven and can exhibit negative transfer. While most prior w…
cs.LG2026
Towards Continuous-time Causal Foundation Models
Dennis Thumm, Ruben Wiedemann, Ying Chen
Extending discrete-time causal Prior-data Fitted Networks for time series to continuous time invites writing the mechanism as a stochastic differential equation (SDE) -- but if the…