Ph.D. Candidate in Applied Statistics
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.
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.
Developing efficient techniques for extracting meaningful insights from large-scale datasets.
Research on joint modeling and analysis of text, image, and other modality data.
Cognitive-inspired reasoning and communication optimization for multi-agent collaboration.
Chain-of-thought reasoning, prompt engineering, and LLM agent frameworks.
Investigating neural network architectures and training methodologies.
LLM cognition, mental health AI, and human-AI interaction.
ACL 2026 (CCF-A), Third Author
Read Paper →ICML 2026 (CCF-A), First Author
Read Paper →Nature Machine Intelligence (SCI-Q1), Fourth Author
Read Paper →IJCAI 2026 (CCF-B), First Author
Read Paper →CogSci 2026 (CCF-B), Corresponding Author
Read Paper →CogSci 2025 (CCF-B), First Author
Read Paper →IEEE Transactions on Cybernetics (SCI-Q1, CCF-B), First Author
Read Paper →ICANN 2025 (CCF-C), First Author
Read Paper →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.
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.
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.
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.