1 citations · 1 across the 5 of their papers we have counts for
4 papers · 1 filter
Causality Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs
Lianghuan Huang, Yingshan Chang
Mechanistic interpretability seeks to uncover how internal components of neural networks give rise to predictions. A persistent challenge, however, is disentangling two often confl…
Learning Model Successors
Yingshan Chang, Yonatan Bisk
The notion of generalization has moved away from the classical one defined in statistical learning theory towards an emphasis on out-of-domain generalization (OODG). There has been…
Language Models Need Inductive Biases to Count Inductively
Yingshan Chang, Yonatan Bisk
Counting is a fundamental example of generalization, whether viewed through the mathematical lens of Peano's axioms defining the natural numbers or the cognitive science literature…
Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation
Yingshan Chang, Yasi Zhang, Zhiyuan Fang +3
The literature on text-to-image generation is plagued by issues of faithfully composing entities with relations. But there lacks a formal understanding of how entity-relation compo…