Into the SAE-verse

Introducing Sparse Autoencoders for mechanistic interpretability.

11 min read   ·   March 27, 2026

2026   ·   machine-learning,   deep-learning,   interpretability,   sae   ·   research

Assorted Notes from CECS1031

77 min read   ·   January 15, 2026

2026   ·   teaching

Flowing with the charts

Summaries of recent papers about flowchart-to-code task. Adapted from my knowledge sharing session at Continental-NTU Corplab.

17 min read   ·   June 23, 2025

2025   ·   data-science,   machine-learning,   deep-learning,   flowchart-understanding,   vlm,   ai   ·   research

Renting GPUs to do Deep Learning homework

Quick tips on renting GPUs to train large ML models.

16 min read   ·   May 03, 2025

2025   ·   data-science,   machine-learning,   deep-learning,   ai   ·   study