Research Interests

Mechanistic Interpretability, Machine Learning Theory, and Selective Inference.

Publications

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

• 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, 2025+. [arXiv][pdf]

Preprints

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

Miscellaneous

• 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.