About Me
Hi! I am a PhD student in the Halıcıoğlu Data Science Institute (HDSI) at UC San Diego, advised by Dr. Biwei Huang. I build scalable causal learning methods that help foundation models and agents learn structured world models—supporting robust generalization and long-horizon decision making.
My recent work spans causal learning from time series at scale, causality-guided world modeling for reinforcement learning generalization, and agentic systems for end-to-end causal analysis. Before joining UCSD, I worked with Dr. Konrad Kording on meta-learning methods on domain-specific causal discovery for large complex systems (e.g., microprocessors). I am also interested in brain-computer interfaces and computational neuroscience, and previously worked on real-time neurofeedback systems advised by Dr. Gan Huang.
- Scalable Causal Learning
- World Models
- Agentic Systems
- Foundation Models
PhD in Data Science, present
University of California San Diego
MSE in Bioengineering, 2023
University of Pennsylvania
BEng in Biomedical Engineering, 2021
Shenzhen University
Exchange Student, 2020
University of Pennsylvania
Experience
Research
Student Researcher
Causal Intelligence Lab @ UCSD- Conducting my PhD research on scalable causal learning, causality-aware world models and foundation models.
Student Researcher
Kording Lab @ UPenn- Conducted large complex system simulations on NMOS6502 microprocessor
- Designed meta-learning algorithms for causal relationship inference
- Collaborated on theoretical deep learning and causal inference research
Student Researcher
MIND Lab @ Shenzhen University- Developed Python-based real-time brain wave visualization tool
- Built multi-module C++ real-time neural feedback system on OpenBCI
- Designed tests to quantify brain wave modulation
Industry
Tech Lead
Abel AI · California, United States- Leading large-scale multimodal causal discovery systems for financial insight mining across heterogeneous data sources.
- Designing and building financial AI agents centered on causal analysis, understanding, and long-horizon reasoning.
- Overseeing data engineering and curation pipelines for web, market, social, and other alternative data streams.
Engineer Intern
Kerry Rehab · Guangdong, China- Developed data processing pipelines for EEG data analysis and modeling
- Assisted with subject recruitment and EEG data collection
Teaching
Teaching Assistant
DSC 291 Topics in Causal Discovery and Representation Learning @ UCSD- Supported an advanced topics course on causal discovery and representation learning for graduate students.
- Advised student projects, from research ideas and experiment design to presentation and write-up.
- Assisted with designing homework and reading discussions that connect theory with current research.
Teaching Assistant
DSC 240 Intro to Causal Inference @ UCSD- Led discussion sections and office hours on core causal inference concepts and problem-solving.
- Graded homework, projects, and exams, providing detailed feedback on modeling and interpretation.
- Helped review and refine course materials, examples, and assignments from a student perspective.
Teaching Assistant
CIS 522 Deep Learning @ UPenn- Led and mentored 15 students in twelve-week deep learning course
- Guided students in designing deep learning projects
- Designed and organized homework and tutorials
Teaching Assistant
Neuromatch Academy Deep Learning- Led and mentored students in three-week deep learning tutorials
- Supported students in building computer-vision projects
- Coordinated logistics with mentors and students
Activity&Accomplishments
Participated in and won silver and bronze medals in the Kaggle Competitions:
- 17th place Sartorius - Cell Instance Segmentation (Top 1%)
- 32nd place UW-Madison GI Tract Image Segmentation (Top 2%)
- 38th place chaii - Hindi and Tamil Question Answering (Top 4%)
- 50th place VinBigData Chest X-ray Abnormalities Detection (Top 4%)
- 73rd place Tabular Playground Series - Nov 2021 (Top 5%)
Fellowships and Awards during acquisition of Bachelor’s Degree:
- Twice Learning Star
- Twice Innovation and Invention Star
- Outstanding Bachelor Thesis
- Honor Prize in the 2019 International Mathematical Contest in Modeling
- Third Place in the 2019 National Biomedical Engineering Design Competition
Projects
Transformer Is Inherently a Causal Learner
Transformers trained autoregressively naturally encode causal structures—gradient attributions directly recover underlying causal graphs.
WM3C: World Modeling with Compositional Causal Components
A novel RL framework that enhances generalization to unseen environments through language-guided compositional causal components.
Causal-Copilot: Autonomous Causal Analysis Agent
A toolkit integrating LLM capabilities and domain expertise for automated causal analysis—enabling researchers to identify causal relationships through natural dialogue.
Learning Causal Discovery
Learn to discover causality inside large complex systems without human prior—tested on MOS 6502 microprocessor.
Millisecond-level Phase Locked Neural Feedback
A millisecond-level phase locked neural feedback system based on OpenBCI for real-time alpha wave regulation.
Sartorius Neuronal Cells Segmentation
A robust deep learning pipeline for segmenting neuronal cells in microscopy images, achieving top 1% on Kaggle.
Recent Publications
Get In Touch
I'm always happy to discuss research collaborations, academic opportunities, or just chat about causality and machine learning.