Welcome to Wizardlancet’s

About Me

I am Zilong Wang, an AI researcher and entrepreneur with a background in clinical medicine. I recently left Microsoft Research Asia (MSRA) to build an Agent-Native Biotech company. This move grows out of my research in AI agents and human–AI interaction, and my interest in how organizations can integrate agents into their work. I see an opportunity for agents to contribute to sustained, complex collaboration and reshape how research is organized and carried forward. We have completed our seed funding round.

Our goal is to address the long timelines and high costs of drug development—often described as 10–15 years and approximately US$2.6 billion—with a particular focus on clinical development and advancement. By integrating agents into research, decision-making, and execution, we aim to help human experts and AI agents work together to shorten development timelines, reduce costs, and bring valuable medicines to patients sooner.

My research spans AI4Health, Foundation Models, and Human–AI Interaction. Previously, I was a Senior Researcher in the Machine Learning Group at MSRA in Shanghai, working on medical foundation models, autonomous agents, and human–AI collaboration. I received my M.D. in Clinical Medicine from Shanghai Medical College, Fudan University, in 2018. Before joining MSRA in 2023, I served as CTO of medical technology startups, leading AI Software as a Medical Device products through development, clinical validation, regulatory approval, and market access. These experiences ground my work in translating technical advances into demonstrable clinical value. I was recognized by Forbes China 30 Under 30 (2020) and Hurun U30 China Entrepreneurship Leaders (2021), and serve on the Executive Committee of the CCF Digital Medicine Technical Committee.

News

Featured Projects

Huabu — A shared, infinite canvas where people and AI agents think and work together. Huabu brings ideas, notes, documents, and outputs from different sessions into a persistent visual Space. Users can organize information with AI, explore connections, and review proposed changes, while connected agents use both the materials and their relationships as context for ongoing work. Website & user handbook.

OpenOE-Lite — An open-source, lightweight reproduction of OpenEvidence-style evidence-based medical Q&A. With just one LLM API key and zero local vector DB, it generates grounded, citation-aligned answers in real time from OpenAlex’s 250M+ open academic works via a 6-stage pipeline (safety gate → 3-view query enhancement → multi-source retrieval → RRF dedup/rank → small-model evidence gating → grounded answer generation). The modular architecture supports smooth upgrade from the Lite core to a Full RAG with local vector DB and clinical guidelines.

Anji-Bridge 安济桥 — A PDF → AI-agent knowledge bridge that converts PDFs into structured, semantic Markdown/JSON ready for LLMs and agents. Built on PaddleOCR-VL for layout-aware OCR and Ovis2.5-9B VLM for image understanding, with AST-level enhancement (heading correction, decorative element filtering, image captioning) and multi-format export. Supports batch processing and base64-embedded portable outputs.

Mandarin Speech Prosody Benchmark (MSPB) — The companion repository for our Interspeech 2025 paper “Can AI Understand Mandarin Speech Prosody?”. MSPB is a linguistically grounded benchmark with 178 phonetically recorded and expert-validated stimuli covering 8 prosody-related tasks (tone/intonation, prosodic ambiguity, focus marking, focus operators, scalar meaning, irony, emotional prosody with/without context). It systematically evaluates how Speech LLMs interpret prosodic cues across phonology, syntax, semantics, and pragmatics.

Contact

• Email: dddwzl3703@gmail.com
• GitHub: wizardlancet

Selected Publications