Jiacheng Lu卢嘉成 卢嘉成Jiacheng Lu
PhD student in CS, Shanghai Jiao Tong University (Zhiyuan Honors) · Shanghai 上海交通大学计算机系博士生(致远荣誉计划) · 上海
About关于
I'm a zero-year PhD student in Computer Science at Shanghai Jiao Tong University, enrolled in the Zhiyuan Honors Program. My research centers on AI for finance, the safety of large language models, and interpretability — spanning topics such as trustworthy financial AI, LLM watermarking, and uncertainty and robustness in model editing. 上海交通大学计算机科学博零,入选博士生致远荣誉计划。研究方向聚焦于 AI 与金融的结合、大语言模型安全与可解释性,涵盖可信金融 AI、大模型水印,以及模型编辑的鲁棒性与不确定性等主题。
Before the PhD I completed a dual-degree undergraduate program in Computer Science and Finance at SJTU, selected for the university's Bole Program for outstanding undergraduates. 本科就读于上海交通大学计算机科学与金融双学位,入选"伯乐计划"上海交通大学卓越本科生培养计划。
Education教育经历
Grants & Fellowships资助与奖学金
Publications论文
- 2026
- 2026
-
2026
Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese PoetryACL 2026
- 2026
- 2026
-
2026
FlyFinBench: Can Data Flywheels Power Benchmark Creation Beyond Model Training?Working paper
-
2026
Rethinking Financial AI Benchmarks: From Workflow Replication to Capital–Asset MatchingPosition paper
-
2026
From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock MarketsPreprint
-
2024
Multi-modal and Metadata Capture Model for Micro Video Popularity PredictionINFORMS Annual Meeting 2024
-
2026
MechPunBench: A Bilingual Mechanism-Centered Benchmark for Pun Understanding and GenerationEMNLP 2026
-
2026
CORD: Server-Client Correspondence Verification for Robust Federated LearningWorking paper
-
2026
Separating Posterior Design from Optimization: A Unified Geometry-Aware Posterior Design for Variational LearningWorking paper
* corresponding author · † equal contribution * 通讯作者 · † 共同第一作者
Patents专利
Seven Chinese patents, including one as first inventor, three as second inventor, and two as co-inventor. 共七项中国专利,其中一项第一发明人、三项第二发明人、两项参与发明。
Academic Service学术服务
Contact联系方式
- Email jack111@sjtu.edu.cn
- Scholar Google Scholar
- GitHub GitHub