Jianliang He

Machine Learning Theory, Mechanistic Interpretability, and Large Language Model.

α-β order denotes alphabetical authorship ordering, and * denotes equal contribution.

How Transformers Learn Causal Structures In-Context: Explainable Mechanism Meets Theoretical Guarantee.
Jianzhe Wei, Siyu Chen, Jianliang He, and Zhuoran Yang.
International Conference on Learning Representations (ICLR), 2026.
In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention.
Jianliang He, Xintian Pan, Siyu Chen, and Zhuoran Yang.
International Conference on Machine Learning (ICML), 2025. [arXiv][pdf] [code] [blog]
From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems.
Jianliang He*, Siyu Chen*, Fengzhuo Zhang, and Zhuoran Yang.
International Conference on Machine Learning (ICML), 2024. [arXiv][pdf]
Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation.
Jianliang He, Han Zhong, and Zhuoran Yang.
International Conference on Learning Representations (ICLR), 2024. [arXiv][pdf]
Harnessing the Collective Wisdom: Fusion Learning using Decision Sequences from Diverse Sources.
(α-β order) Trambak Banerjeea, Bowen Gang, and Jianliang He.
Biometrika, 2026. [arXiv][pdf]

On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking.
Jianliang He, Leda Wang, Siyu Chen, and Zhuoran Yang.
Submitted, arXiv.2602.16849, 2026. [arXiv][pdf] [code] [blog]
Data-light Uncertainty Set Merging with Admissibility.
Shenghao Qin*, Jianliang He*, Qi Kuang*, Bowen Gang, and Yin Xia.
Submitted, arXiv:2410.12201, 2024. [arXiv][pdf]

False Discovery Control in Multiple Testing: A Selective Overview of Theories and Methodologies. [pdf]
Short Version as a Book Chapter in ICSA Book Series in Statistics: Big Data Analytics in Biostatistics and Bioinformatics.