Siyu Chen

Taming Polysemanticity in LLMs: Theory-Grounded Feature Recovery via Sparse Autoencoders

Interpreting Multi-Layer Transformers for In-Context Linear Regression with Varying Covariance

How Transformers Learn Causal Structures In-Context: Explainable Mechanism Meets Theoretical Guarantee

Unlocking Out-of-Distribution Generalization in Transformers via Latent Space Reasoning

Learning to Incentivize on the Fly: Leader-Follower Games with Policy Recommendation

Mechanistic Interpretability of In-Context Learning Generalization through Structured Task Curriculum

On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds

In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention

Exploration in the Face of Strategic Responses: Provable Learning of Online Stackelberg Games

Quantile-Optimal Policy Learning under Unmeasured Confounding

Steer a Crowd: Learning to Persuade a Population in a Stackelberg Game