Qiankang (Kant) Wang
Machine learning for biology — representation learning, foundation models, and scientific computing.
qkwang@berkeley.edu ·
GitHub ·
LinkedIn
Education
B.A. Data Science, University of California, Berkeley — Class of 2027.
Research
- Stanford University — Research Assistant, Mar 2026 – Present.
- Computational Biophysics Lab, UC Irvine — Research Assistant, Jul 2024 – Nov 2025. GPU-accelerated solvers and Slurm workflow infrastructure for PBSA-style biomolecular simulations.
Publication
Wu, Y., Wang, Q., et al. (2026).
AmberTorchPB: A Unified Framework for Poisson–Boltzmann-Based Reaction Field Energy Calculation via Tensor Computation.
Journal of Chemical Theory and Computation.
Selected projects
- simclr-cifar10-pytorch — SimCLR self-supervised learning on CIFAR-10 with ResNet-18 + k-NN eval.
- regal — AI legal-ops platform with real-time deposition transcription.
- Decision-Tree — from-scratch C++ decision-tree classifier (Gini impurity, Titanic dataset).
Skills
ML: Foundation models, transformers, self-supervised learning, PyTorch, LibTorch.
Scientific computing: GPU optimization, CG / BiCG solvers, Poisson–Boltzmann / PBSA, molecular simulation.
Languages: Python, C++, Bash, SQL.
Tools: Linux, Git, Slurm, CMake, LaTeX.
This is a text-only fallback. The interactive site requires JavaScript.