Blog

Home Research Publications Projects Service Updates Blog CV

Planned short essays on GenAI optimization, AI hardware security, papers, experiments, and lessons from research engineering. I plan to publish weekly or monthly once the first posts are ready.

Planned Posts

How to Evaluate GenAI Optimization Beyond Demo Quality

Evaluation sets, latency budgets, regression testing, and measuring whether an optimization actually helps.

What Bit-Flip Attacks Reveal About Multimodal LLMs

A practical note on model faults, accelerator reliability, and security-aware evaluation.

Temporal Logic as a Tool for AI Model Compression

Why formal specifications can guide compression and deployment decisions for edge AI.