activity
20242026
most citedAssessing and improving reliability of neighbor embedding methods: a map-continuity perspective

1 citations · 1 across the 4 of their papers we have counts for

collaborators

5 papers

cs.LG2026

How Does Unfaithful Reasoning Emerge from Autoregressive Training? A Study of Synthetic Experiments

Fuxin Wang, Amr Alazali, Yiqiao Zhong

Chain-of-thought (CoT) reasoning generated by large language models (LLMs) is often unfaithful: intermediate steps can be logically inconsistent or fail to reflect the causal relat…

cs.LG2026

Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic

Xingyu Zhao, Darsh Sharma, Rheeya Uppaal +1

Large language models (LLMs) often achieve strong benchmark accuracy yet remain brittle under small distribution shifts. While recent mechanistic studies reveal the discrepancy bet…

cs.CL2025

Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning

Haolin Yang, Hakaze Cho, Yiqiao Zhong +1

The unusual properties of in-context learning (ICL) have prompted investigations into the internal mechanisms of large language models. Prior work typically focuses on either speci…

math.ST2025

A statistical theory of overfitting for imbalanced classification

Jingyang Lyu, Kangjie Zhou, Yiqiao Zhong

Classification with imbalanced data is a common challenge in data analysis, where certain classes (minority classes) account for a small fraction of the training data compared with…

stat.ME2024★ 1 cited

Assessing and improving reliability of neighbor embedding methods: a map-continuity perspective

Zhexuan Liu, Rong Ma, Yiqiao Zhong

Visualizing high-dimensional data is essential for understanding biomedical data and deep learning models. Neighbor embedding methods, such as t-SNE and UMAP, are widely used but c…