2 papers
cs.CV2026
SciFigure2Code: An AI-Reconstructed Benchmark for Scientific Figure-to-Code
Wentao Li, Yibo Wu, Yizhe Chen +5
Scientific figures are the interface through which research claims are inspected and reused, but final published panels rarely expose the data or plotting code that produced them.…
cs.LG2025
Bias as a Virtue: Rethinking Generalization under Distribution Shifts
Ruixuan Chen, Wentao Li, Jiahui Xiao +3
Machine learning models often degrade when deployed on data distributions different from their training data. Challenging conventional validation paradigms, we demonstrate that hig…