CV

Education

Ph.D. in Computer Science, University of Illinois Chicago, 2025 – present
- Advisor: Prof. Lu Cheng; Collaborator: Prof. Kun Zhang (CMU)
- Research: Causal Representation Learning, Reinforcement Learning, LLM Alignment, AI for Science
B.Eng. in Automation (Control & Robotics), Zhejiang University, Chu Kochen Honors College, 2021 – 2025
- GPA: 3.98/4.0, Rank: 6/121 (Top 5%), Outstanding Graduate

Shicheng Fan, Kun Zhang, Lu Cheng. “TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning.” Under Review, arXiv:2601.21135
Hanyu Su, Shicheng Fan, Yifan Cui, Lu Cheng. “Conformalized Proximal Causal Inference with a Single Proxy.” Under Review

TRACE: CRL under Continuous Mechanism Evolution · First Author · 2025–2026
- Proposed the first theoretical framework extending causal representation learning from discrete mechanism shifts to continuous transitions; proved joint identifiability via nonlinear ICA and variational inference
- Designed the TRACE framework based on Mixture-of-Experts, recovering mechanism trajectories via time-varying mixture coefficients, generalizable to unseen intermediate states
Knowledge-Enhanced RL for LLM Factuality Alignment · Co-1st Author · 2025–present
- Designing an end-to-end LLM post-training pipeline combining SFT and RL for improved factuality alignment
Causal Representation Learning for Protein Conformational Transitions · 1st Author · 2025–present
- Applying causal representation learning to molecular dynamics for identifying key residues driving protein conformational transitions
Semantic and Goal-Driven Dexterous Hand Manipulation · B.Sc. Thesis · 2024–2025
- Reproduced the Text2HOI three-stage framework, matching reported performance on H2O, GRAB, and ARCTIC datasets
- Proposed a Shadow Hand → MANO cross-embodiment retargeting algorithm; joint training with GraspM3 dataset improved Physical Realism to 0.897 and reduced penetration volume by ~50%

ASC Student Supercomputer Challenge, National Second Prize, 2024
ACM-IPCC International Parallel Computing Challenge, National Second Prize, 2022

Programming: Python, C/C++
Frameworks & Tools: PyTorch, HuggingFace Transformers, verl/TRL, Git, LaTeX, Linux/HPC (NCSA Delta, NRP Nautilus), CUDA, MPI
Research Areas: Causal Inference & Causal Representation Learning, LLM Alignment & Anti-Hallucination, Diffusion Models, Embodied Intelligence
Languages: Chinese (native), English (fluent)