Notes
Research notes, engineering lessons, and ideas in progress.
Short technical writing on ML reliability, numerical debugging, GPU portability, software engineering, and the practical decisions behind research systems.
May 1, 2026
What I Want This Blog to Become
Academic papers are necessarily compressed. They describe the method, the evaluation, and the result, but they often leave out the messy middle: why a test design changed, why o...
Read note → July 8, 2025Automatically Detecting Numerical Instability in ML via Soft Assertions
In our FSE 2025 paper, we introduce Soft Assertions — a new approach to detect and trigger these hidden bugs automatically.
Read note → July 7, 2025Testing GPU Numerics: Finding Numerical Differences Between NVIDIA and AMD GPUs
Our SC24-W workshop paper presents a systematic method to detect and analyze these cross-vendor numerical differences.
Read note →