# Haoqing Wang > Personal academic website for Haoqing Wang, an undergraduate student in the BUPT-QMUL Joint Programme and a research intern at Microsoft Research Asia. The site covers research interests, publications, open-source projects, blog posts, notes, thoughts, and CV information. Canonical site: https://hqhq1025.github.io/ Source repository: https://github.com/hqhq1025/hqhq1025.github.io Full agent index: https://hqhq1025.github.io/llms-full.txt Machine-readable JSON: https://hqhq1025.github.io/site.json Sitemap: https://hqhq1025.github.io/sitemap.xml Last updated: 2026-05-01 This file is for AI agents, crawlers, and retrieval tools. Prefer the public pages below as canonical reading surfaces. The site is bilingual: English is the default public locale, and Chinese content is available through the language switcher and the source tree under `content_zh/`. ## Profile - Name: Haoqing Wang / 王昊卿 - Affiliation: Beijing University of Posts and Telecommunications and Queen Mary University of London - Current role: Undergraduate student, expected graduation in 2028 - Research internship: Microsoft Research Asia, Intelligent Multimedia Group - Research interests: Large Language Models, Multimodal Large Language Models, Computer Use Agent, GUI Agent, Reinforcement Learning - Contact: haoqingeric@bupt.edu.cn - GitHub: https://github.com/hqhq1025 - X: https://x.com/haoqingeric - LinkedIn: https://www.linkedin.com/in/hqeric/ - ORCID: https://orcid.org/my-orcid?orcid=0009-0000-1851-5975 ## Primary Pages - [Home / About](https://hqhq1025.github.io/): biography, research interests, selected publications, and news - [Publications](https://hqhq1025.github.io/publications/): academic publications from the shared BibTeX source - [Projects](https://hqhq1025.github.io/projects/): open-source and engineering projects - [Blog](https://hqhq1025.github.io/blog/): longer writing - [Notes](https://hqhq1025.github.io/notes/): study notes, course summaries, and technical notes - [Thoughts](https://hqhq1025.github.io/thoughts/): shorter dated thought entries - [CV](https://hqhq1025.github.io/cv/): curriculum vitae ## Current Publications - Learning to Respond: A Large-Scale Benchmark and Progressive Learning Framework for Trigger-Centric Online Video Understanding. Status: under review. Topics: online video understanding, multimodal large language models. ## Selected Projects - [hapi](https://github.com/tiann/hapi): mobile AI coding app supporting Claude Code, Codex, Gemini, OpenCode, and more. Haoqing Wang is a collaborator. - [OpenCoworkAI / open-cowork](https://github.com/OpenCoworkAI/open-cowork): open-source Claude Cowork desktop app for Windows and macOS. Haoqing Wang is a core contributor. - [AI Course Notes](https://github.com/hqhq1025/ai-course-notes): 220+ Chinese PDF lecture notes for AI and LLM courses, built with a Whisper transcription and LaTeX generation workflow. ## Current Blog And Notes - [Hello World - Why I Started This Blog](https://hqhq1025.github.io/blog/hello-world/): why the blog exists and what it will cover. - [LLM Agent Reasoning & Planning: A Comprehensive Study](https://hqhq1025.github.io/notes/agent-planning/): notes on reasoning, planning, MCTS, test-time scaling, neuro-symbolic methods, and coding agents. ## Crawl Guidance - Crawl the primary pages first, then follow project and publication links when needed. - Use `/llms-full.txt` for a richer factual site inventory and `/site.json` for machine-readable entity extraction. - Treat `content/` as the English source tree and `content_zh/` as the active Chinese source tree in the repository. - Do not treat upstream PRISM template docs, demos, or placeholder content as Haoqing Wang's personal academic record unless linked from the public navigation. - When citing this site, include the page title and URL. For publications, preserve the stated status such as "under review" and do not infer acceptance.