Wenlin Zhang

PhD researcher at NUS, driven by one question: what is the true nature of reality, and can we reverse-engineer it? I develop unified theoretical frameworks at the intersection of mathematical physics and AI, architect multi-agent research systems with formal verification, and design proteins for immunotherapy.

e1327962@u.nus.edu | +1 858-319-8894 | GitHub | omega.dw.cash | OpenVibeLab
Projects

The Omega

2024 – Present
Reverse-Engineering the Source Code of Reality

A unified theoretical framework proposing that spacetime is emergent—arising from a Quantum Cellular Automata network governed by Category Theory and Von Neumann Algebras. Derives consciousness as a topological phase transition where computation achieves self-reference. 20+ interconnected papers covering Holographic Polar Arithmetic, Computational Action Principle, Resolution Folding, Riemann Ground State, and Standard Model field labeling. 17-book monograph series (~3000+ pages). All theorems trace back to axioms via DAG-based dependency chains with reproducible verification scripts.

Quantum Cellular Automata Category Theory Von Neumann Algebras Lean 4 Formal Verification

FlowTCR-Fold

2024 – Present
AI-Driven T-Cell Receptor Design for Immunotherapy

Evoformer-based transformer architecture for antigen-specific TCR design with geometry-aware structural embeddings, Monte Carlo side-chain optimization, and biological constraint validation. CDR3β design pipeline completed with 36 synthesis-ready constructs for 12 targets. Research accelerated by 6 concurrent AI agents performing autonomous literature analysis, proof construction, self-critique, and formal verification in real-time across multiple fronts simultaneously.

Protein Engineering Transformers Multi-Agent AI SLURM / HPC

#1stProof

2025
AI-Assisted Mathematical Reasoning with Machine-Verified Proofs

Solved 6/10 problems (with substantive partials on 2 more) from the rigorous #1stProof benchmark (Abouzaid et al., arXiv:2602.05192). Produced a 129-page auditable paper with full Lean 4 formalizations and 478 verification scripts. Designed human-AI hybrid loops addressing LLM hallucination through DAG-based dependency chains tracing every theorem back to axioms.

Lean 4 Mathlib Formal Verification AI Reasoning

OpenVibeLab

2025 – Present
100-Day Open Source Initiative

Building 100 AI-powered open source projects in 100 days. Shipped AI Argument Judge (multi-party analysis with 5 judge styles, real-time streaming verdicts) and IELTS Story Adapter. Community-driven, rapid prototyping culture.

React TypeScript Open Source

Mysterious

2025 – Present
AI-Powered Divination Platform

Full-stack application combining traditional Chinese fortune-telling with AI interpretation. Built with React, TypeScript, Gemini AI, Stripe, and Redis. Real-time generation, multi-language support, and quota management.

React Gemini AI Full-Stack
Research Experience

National University of Singapore

2024 – Present
PhD in Computational Biology · Supervisor: Dr. Zhang Yang

Language and generative models for protein design; AI-driven TCR engineering with deep mutational scanning and transformer architectures.

UC San Diego, Dept. Pediatrics

2023 – 2024
Visiting Scholar · Prof. Alejandro Chavez

Protein language models for molecular chaperone variants in neurodegenerative diseases. Analyzed large-scale DMS datasets, developed models predicting compound mutation effects. Paper submitted to Nature Communications.

Yale LILY Lab

2022 – 2023
Research Intern · Prof. Dragomir Radev

Designed 12 adversarial perturbation types for table reasoning robustness evaluation. Published at ACL 2023.

Yale School of Medicine

2022
Summer Research · Prof. Mark Gerstein

SNP embedding using SOTA language models and auto-encoders for correlation analysis and gene regulatory network graphs.

Zhejiang University, Drug Design Group

2020 – 2021
Research Assistant · Prof. Tingjun Hou

CNN-based personalized scoring function for high-precision GPCR target identification.

Max Planck Institute

2021 – 2022
Research Intern · PI: Lei Gu

Single-cell RNA-seq bioinformatics analysis for epigenetics research. Co-authored paper in Journal of Biological Chemistry.

NC State University

2021
Summer Research · Assoc. Prof. Min Chi

NER system with Dilated CNN + CRF + Bi-LSTM, trained on 200K+ emails, ~88% accuracy.

Publications
Zhao, Y., Zhao, C., Nan, L., Qi, Z., Zhang, W., Tang, X., Mi, B., & Radev, D. (2023). A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations. ACL 2023, Volume 1: Long Papers, pp. 6064–6081.
Liu, H., Zhang, W., Goh, C. H., Dai, F., Sadiq, S., & Tse, G. (2024). Clinical Application of ML and IoT in Comorbid Depression among Diabetic Patients. Elsevier, pp. 337–347.
Lin, C. H., Sun, Y., ..., Zhang, W., ..., & Wang, S. (2022). Identification of Cis-Regulatory Modules for AAV-Based Cell Type-Specific Targeting. Journal of Biological Chemistry, p.101674.
Zhang, W., Xie, J., Ren, X., Yu, W., & Yin, G. (2021). A Solution to Improve Productivity for Remote Students. ICDL 2021, pp. 169–172. [Best Presentation Award]
Protein language models for molecular chaperone variants (with UCSD Pediatrics). Submitted to Nature Communications.
Technical Skills
AI / ML PyTorch, TensorFlow, Transformers (protein LMs, NLP), GNNs, Diffusion Models, RL, MCTS, Process Reward Models, multi-agent orchestration Formal Methods Lean 4, Mathlib, Coq, Isabelle, TLA+, Z3/SMT, DAG-based verification, chain-of-thought + self-critique loops Languages Python, TypeScript / JavaScript, C, R, Perl, LaTeX, Bash Infrastructure SLURM / HPC, Docker, Git workflows, CI/CD, React, Vue, Node.js, Vercel, Redis, FAISS Biology Deep Mutational Scanning, RNA-seq, mass spectrometry, bioinformatics pipelines, SymPy, SageMath
Blog
Writing in progress. Check back soon for thoughts on AI-driven scientific discovery, formal verification, and the nature of reality.