Zhenke Duan

Ph.D. Candidate in Applied Statistics

Scroll
ZD

About Me

I hold a M.S. in Applied Statistics (Data Science) from ZUEL. My research centers on data mining, multimodal analysis, and cognitive-inspired multi-agent reasoning. I have hands-on experience with open-source projects and am proficient in PyTorch, TensorFlow, LangChain, and vLLM.

"Fake it until you make it."

I also have strong Linux-based full-stack development skills and programming experience in Python, R, and Java. I am passionate about building open-source research platforms and applying machine learning to solve real-world problems.

Ph.D. in Applied Statistics Zhongnan University of Economics and Law, 2026 - Present
M.S. in Applied Statistics Zhongnan University of Economics and Law, 2024 - 2026
B.S. in Financial Mathematics Zhongnan University of Economics and Law, 2020 - 2024
Institute Institute for AI Optimization and Decision Science (AIODS), ZUEL
Founder & CTO CodeSoul.co (Hangzhou Lingmu Chuangxiang Technology Co., Ltd.)

Research Interests

Data Mining

Developing efficient techniques for extracting meaningful insights from large-scale datasets.

Multimodal Analysis

Research on joint modeling and analysis of text, image, and other modality data.

Multi-Agent Systems

Cognitive-inspired reasoning and communication optimization for multi-agent collaboration.

Large Language Models

Chain-of-thought reasoning, prompt engineering, and LLM agent frameworks.

Deep Learning

Investigating neural network architectures and training methodologies.

Cognitive Science

LLM cognition, mental health AI, and human-AI interaction.

Publications

2026

Tree-CoT-RT: An Explainable Multi-Path Tree-Guided Chain-of-Thought and Reinforcement Learning Framework for Aspect Sentiment Quad Prediction

ACL 2026 (CCF-A), Third Author

Read Paper →
2026

Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers

ICML 2026 (CCF-A), First Author

Read Paper →
2026

Building a causality-aware single-cell RNA-Seq foundation model via context-specific causal regulation modeling

Nature Machine Intelligence (SCI-Q1), Fourth Author

Read Paper →
2026

CRFormer: Covariance-Enhanced Rough Transformer for Multivariate Time Series Modeling

IJCAI 2026 (CCF-B), First Author

Read Paper →
2026

Structural Alignment of Mental Health Categories in LLM Representation Space

CogSci 2026 (CCF-B), Corresponding Author

Read Paper →
2025

KG-MASD: Knowledge-Graph-Guided Multi-Agent Collaboration and Distillation

Information Systems (SCI-Q2, CCF-B), Co-First Author

Paper → GitHub →
2025

ECCoT: A Framework for Enhancing Effective Cognition via Chain of Thought in Large Language Models

CogSci 2025 (CCF-B), First Author

Read Paper →
2026

BEAM: A Bayesian Energy-Aware Framework for Multi-Agent Communication Optimization

IEEE Transactions on Cybernetics (SCI-Q1, CCF-B), First Author

Read Paper →
2025

MENGLAN: Multiscale Enhanced Nonparametric Gas Analyzer with Lightweight Architecture

ICANN 2025 (CCF-C), First Author

Read Paper →
2025

YOLO-FireAD: Efficient Fire Detection via Attention-Guided Inverted Residual Learning and Dual-Pooling Feature Preservation

ICIC 2025 (CCF-C), Corresponding Author

Paper → GitHub →

Projects

THETA: LLM-Enhanced Topic Analysis Platform

GitHub →

Developed an open-source research platform for topic analysis in social science, integrating domain-adaptive document embeddings from Qwen-3 models with generative topic modeling workflows. Built support for zero-shot, supervised, and unsupervised embedding modes.

AgentInferKit: Modular Platform for Agent Inference

GitHub →

Built a modular platform for LLM/VLM/Agent systems across text, multimodal, retrieval-augmented generation, and tool-use tasks. Designed core components including model adapters, reasoning strategies, RAG pipelines, and evaluation modules.

OpenLab: Email-Triggered Automated Experiment Runner

GitHub →

Developed an open-source automation system that allows users to submit ML/DL/statistical experiment requests via email, with Claude Code handling experiment planning, code generation, execution, and result packaging.

SOMAS: Online Reinforcement Learning Framework

GitHub →

An online memory and communication-graph optimization framework for multi-agent systems using Swarm and LangGraph. Has earned over 500+ GitHub stars. Improves deployment accuracy by about 40% over existing solutions.

Contact

Get in Touch

15982498982

Wuhan, China