Author

Jun-Jie Yao

h-index 4 View on Semantic Scholar

We have 3 of 10 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

Probability-Signature Dynamics: Unpacking Modular Addition Learning Within Two-Layer Networks

Neural networks trained on modular addition tasks often develop Fourier-structured representations that support exact generalization. While prior work has identified these Fourier circuits, the mechanism by which gradient-based training selects them from the data distribution remains unclear. We address this question u...

Yun-Jing Wang, Jun-Jie Yao, Lin-Yu Liu et al. · 0 citations

#artificial intelligence Preprint Sep 2026

CADOC: Cache-Aware Dynamic Object Context for Long-Horizon Agents

CADOC (Cache-Aware Dynamic Object Context), an online algorithm that replaces structured objects with compact Cards while preserving exact, on-demand retrieval of their original contents, is proposed, demonstrating that efficient compression depends not only on shortening prompts but also on scheduling edits to preserv...

Jun-Jie Yao, Zhang-Chen Zhou, Zhi-qin John Xu · 0 citations

#machine learning Preprint Aug 2026

Context Staircase: Signature-Aligned Dynamics of Token Embeddings under Small Initialization

A dynamic explanation of how data statistics and architecture jointly shape token embeddings in language models is provided, and an implicit bias in the space of data statistics is revealed: training proceeds from simpler, low-order statistical relations toward increasingly complex, context-dependent ones.

Jun-Jie Yao, Liangkai Hang, Zhi-qin John Xu · 0 citations