Experience & education.

Applied Scientist Intern · Amazon Rufus

Hosts: Zoey Li and Zhenyu Shi

• Developed a Muon recipe for RLVR with no momentum, achieving 29.17% macro-averaged Pass@1 on Qwen3-4B-Base compared with 24.47% for AdamW across three math benchmarks.
• Used spectral diagnostics and checkpoint interventions to study optimization stability and how learned behavior is organized across singular directions and attention projections.
• Investigated RLVR trajectory predictability with random-walk controls. Read the research write-up ↗

Ph.D. Student · University of Illinois Urbana-Champaign

Computer Science · Advisor: Prof. Tong Zhang

• Developed Adaptive Layerwise Perturbation (ALP) to stabilize off-policy LLM reinforcement learning under policy staleness and training–inference mismatch.
• Proposed DIPNeT for generalization across reasoning and adversarial robustness settings.
• Developed GVM-RAFT, a prompt-specific sample allocation strategy, achieving a 2–4× speedup and improved accuracy over vanilla RAFT.
• Studied feature decoupling in Transformers and their expressiveness for hidden Markov processes, and explained how ensemble methods reduce overadaptation in supervised fine-tuning.

MPhil · Hong Kong University of Science and Technology

Mathematics · Advisor: Prof. Tong Zhang

Studied the harmful effects of benign overfitting on adversarial robustness, and how spurious feature diversification and overparameterization affect out-of-distribution generalization. Supported by the Hong Kong PhD Fellowship.

B.S. in Statistics · University of Science and Technology of China

School of the Gifted Young

Ranked 5/91 in Statistics; outstanding graduate.