Haonan Zhang
PhD Candidate
Sichuan ⇌ Beijing, United States
Summary
🤩
RockstarHaonan Zhang is a PhD candidate with eight years of experience focused on LLM-agents and vision-language research, bridging academic rigor with practical machine learning engineering. Based between Sichuan and Beijing but linked to the United States, he brings an international perspective to cross-disciplinary AI problems. His work centers on integrating language models with visual understanding to build interactive, agentic systems that perceive and act. Although early in his publication profile, his sustained GitHub presence as a PhD researcher signals active experimentation and rapid prototyping of novel multimodal approaches. Colleagues can expect a researcher who combines deep technical curiosity with the discipline to translate complex models into usable research artifacts.
8 years of coding experience
Github Skills (98)
attention-mechanism10
dialog10
encoder10
computer-vision10
classification10
agent10
image-classification10
visual-question-answering9
transformers9
natural-language-generation9
dialogue-systems9
artificial-intelligence9
nlp8
chatbot8
conversational-ai8
Programming languages (8)
Github contributions (5)
zchoi/zchoi
Jul 2022 - Jan 2023
Contributions:45 commits, 2 PRs, 97 pushes in 6 months
zchoi/Awesome-Embodied-Robotics-and-Agent
Jul 2023 - Mar 2025
This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the latest updates! 🔥
Contributions:1 review, 9 PRs, 166 pushes in 1 year 8 months
agentembodied-agentembodied-ailarge-language-modelmanipulator-robotics
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.