CV
Education, research experience, publications, projects, and technical skills.
Contact Information
| Name | Haotian Zhong |
| haotian7.zhong@gmail.com | |
| Website | https://htzhong.top |
Education
-
2024 - present Beijing, China
B.S.; B.Eng.
Tsinghua University
Mathematics and Physics; Software Engineering
-
2027 - 2027 Berkeley, CA
University of California, Berkeley
UCEAP Exchange Program
- Selected for Tsinghua University’s sponsored exchange program, with one seat per department.
Research Experience
Publications
-
2026 Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory
* Co-second authors. Co-developed CoMem, a Qwen3-8B memory architecture that caches intermediate residual states and recomputes query-conditioned upper layers for efficient long-context memory.
Projects
-
2026 - 2026 FinAgent OS: Multi-Agent Wealth Management System
Group project for the Software Engineering course
- Built a LangGraph- and FastAPI-based multi-agent system for user profiling, asset screening, market timing, critic review, and compliance auditing across 54 instruments in nine asset classes.
- Implemented Markowitz optimization, risk parity, Monte Carlo simulation, VaR and CVaR, stress testing, backtesting, and performance attribution.
- Integrated AkShare and yfinance data, persistent SQLite sessions, Docker deployment, and GitHub Actions CI while maintaining a 269-test passing baseline.
-
2025 - 2026 TASIVE: Transformer-Based Siamese Signature Verification
Lead developer; major project for the Deep Learning course
- Developed a Swin-T Siamese network with a lightweight MLP projection head, L2-normalized 128-dimensional embeddings, and a scaled cosine binary-cross-entropy objective.
- Designed a strict writer-disjoint train and validation split and evaluated on a fixed all-pairs validation set of 5,748 signature pairs.
- Achieved 99.98% accuracy, 1.0000 ROC-AUC, and 0.0000 EER, outperforming a reproduced SigNet baseline under the same protocol.
Technical Skills
Programming: Python, C++, SQL
Machine Learning and Research: PyTorch, Hugging Face Transformers, CUDA, LLM post-training, agent evaluation, contrastive learning
Systems and Data: Linux, Git, NumPy, Pandas, Weights & Biases, Docker, SQLite, Slurm, LaTeX
Languages: Mandarin Chinese (native); English (TOEFL iBT 100, Speaking 26)