Alex Lu Chen

While I was an undergraduate at UCLA, I conducted research at the StarAI Lab (Prof. Guy Van den Broeck) and MINT Group (Prof. Aditya Grover), with a focus on more efficient inference algorithms, particularly in LLM caching. Earlier, I worked with Prof. Katsushi Arisaka, helping develop software for a robotic dissection system.

Between research projects, I’ve also interned at Ramp and Amazon. At Ramp, I built re-evaluations for accounting transaction categorization and adapted KV Cache Compression for state-of-the-art models. At Amazon, I built a debugger for ML models to improve traceability across recommendations.