Curriculum Vitae · November 2026

Qiankang (Kant) Wang

qkwang@berkeley.edugithub.com/wangkant (opens in new tab)

Education

Aug 2025–May 2027

University of California, Berkeley

B.A. in Data Science · Berkeley, CA

GPA3.82 / 4.00

CourseworkIntroduction to Machine Learning (COMPSCI 189) · Natural Language Processing (EECS 183) · Concepts of Probability (STAT 134) · Introduction to Computational Molecular and Cell Biology (BIOENG C131)

Jan 2023–May 2025

Diablo Valley College

Data Science · Pleasant Hill, CA

GPA4.00 / 4.00

CourseworkLinear Algebra (MATH 194) · Differential Equations (MATH 294) · Elementary Statistics with Probability (MATH 142) · Introduction to Data Science (COMSC 156) · Program Design and Data Structures (COMSC 210)

Honors and Awards

Aug 2026–Present

Data Science Honors Program, University of California, Berkeley

Dec 2025

Dean’s List, UC Berkeley College of Computing, Data Science, and Society

Research Interests

Machine learning for DNA and protein sequences · Self-supervised and generative models · Inductive biases from known biology

Publications

2026

AmberTorchPB: A Unified Framework for Poisson–Boltzmann-Based Reaction Field Energy Calculation via Tensor Computation

Wu, Y.; Wang, Q.; Jiang, R.; Luo, R.

Journal of Chemical Theory and Computation, 22(7), 3554–3570. https://doi.org/10.1021/acs.jctc.6c00085 (opens in new tab)

Research Experience

Jul 2024–Feb 2026

Iterative Poisson–Boltzmann Solvers for AmberTorchPB

Ray Luo Lab · University of California, Irvine

  • Implemented conjugate gradient (CG) and biconjugate gradient solvers in AmberTorchPB, a LibTorch framework for Poisson–Boltzmann reaction-field energies on CPU and GPU.
  • Built a Slurm pipeline that ran over one million Poisson–Boltzmann surface area (PBSA) energy calculations to benchmark accuracy, runtime, and memory across precisions; under identical settings, the CG solver matched AMBER PBSA energies (R² = 1.00) while running over 2× faster on CPU and nearly 2× faster on GPU.
May 2026–Oct 2026

Sequence-to-Function Models: AlphaGenome and ChromBPNet

Anshul Kundaje Lab · Stanford University

  • Retrained ChromBPNet on AlphaGenome’s data split, aligning input windows and evaluation loci to enable a fair comparison on identical held-out K562 regions.
  • Probed layer embeddings from AlphaGenome and ChromBPNet with linear probes and UMAP under a shared, overlap-aware cross-validation protocol, testing which results hold across embedding readouts.
  • Built an open-source pipeline that applies identical attribution (DeepLIFT/DeepSHAP), motif discovery (TF-MoDISco), and hit calling (FiNeMo) to AlphaGenome and ChromBPNet.

Codegithub.com/wangkant/motifline (opens in new tab)

Independent Projects

Mar 2026

Self-Supervised Contrastive Pretraining on Tiny-ImageNet

github.com/wangkant/simclr-pytorch (opens in new tab)

Implemented SimCLR-style self-supervised learning with a ResNet-18 encoder and an alignment-and-uniformity objective in PyTorch. Pretrained on 100,000 unlabeled Tiny-ImageNet-200 images for 45 epochs, achieving 26.2% top-1 accuracy on the 200-class validation set using frozen encoder features and a cosine k-NN classifier (k = 20).

May 2026–Present

Conversational LLM Agent with Evidence-Gated Behavioral Updates

github.com/wangkant/personagent (opens in new tab)

Developed an open-source conversational LLM agent with evidence-gated behavioral updates from user feedback, including audit logs and rollback. Designed an evaluation suite with a prompt-only baseline, repeated trials, and confidence intervals to assess whether feedback carries over to later interactions.

Technical Skills

Programming languages
Python, C++, Java, MATLAB, Bash, SQL
ML frameworks
PyTorch, LibTorch, TensorFlow, scikit-learn
ML methods
Transformers, convolutional networks, contrastive and self-supervised learning, diffusion models
Attribution analysis
DeepLIFT, DeepSHAP, TF-MoDISco, FiNeMo
Scientific computing
GPU optimization, iterative linear solvers, Poisson–Boltzmann and PBSA pipelines, molecular simulation workflows
Tools and systems
Linux, Git, Docker, CMake, Slurm, Jupyter, LaTeX

Leadership & Service

Sep 2023–Jun 2024

Founder & President, CogniTech Explorer Club

Diablo Valley College

Founded an AI and cognitive science club and organized introductory machine learning workshops.

Jan 2024–Dec 2024

President, National Alliance on Mental Illness (NAMI) Club

Diablo Valley College

Organized mental health activities and connected students with NAMI Contra Costa resources and volunteering.