Andrew
Lin

UT Dallas — Prof. Xinfang Jin · GAN-based 3D microstructure generation

• Built a Python preprocessing pipeline converting DREAM.3D exports into 64³ voxel stacks with measured volume fractions and surface areas — replacing an entire MATLAB workflow, with batch --multi and spatial --tile-xy modes for 500³+ volumes.
• Diagnosed two bugs causing pore-phase collapse in a WGAN-GP, then designed a differentiable connectivity loss (3D-convolution isolation penalty + percolation term) — raising pore-connectivity and active-TPB similarity from FAIL to OK: 0.48 → 0.90 and 0.59 → 0.86.
• Built 4_CNNCT, an analysis module for phase percolation, triple-phase-boundary density, and tortuosity — shipped with a 23-test suite.
• Automated a manual ParaView workflow with pvpython; its ground-truth test harness caught 4 silent label-corrupting bugs before handoff.
• Ran the full pipeline end-to-end: CNN estimator → connectivity-aware WGAN-GP → persistent-homology validation → transport validation.

UT Dallas Summer Research Program — Dr. Yapeng Tien's Computer Vision Lab

• Studied active speaker detection on datasets in the AVA Active Speaker format.
• Optimized training with VGG16 transfer learning and selective weight freezing to maximize mAP.

UT Dallas CAST Lab — Dr. Wei Li

• Researched hybrid manufacturing and CAD modeling; designed, coded, and simulated milling paths for medical and automation applications.

• Led weekly tutoring sessions guiding underclassmen through CS concepts and live debugging.
• Built the mentorship muscle that now shows up in every code review and pair-programming session.

• Competed at the national level hardening Windows, Linux, and Cisco systems under time pressure.

• Competitive coding in Swift and Python; member of the Computer Science Honor Society.