Kai-Jie Lin (KJ) 林楷傑
linkai0508 [at] gmail [dot] com
I am an M.S. student in Electrical and Computer Engineering at Carnegie Mellon University. I am working on RL-Kernel , an open-source library of bitwise-consistent CUDA/Triton kernels for RL post-training. My research interests are Reinforcement Learning, Large Reasoning Models, and Machine Learning Systems.
Previously, I was an Research Assistant in the Reinforcement Learning and Bandits Lab at NYCU and an Machine Learning Engineer at Rayleigh Vision Intelligence, building multimodal machine learning systems for production lines. I received my B.S. in Computer Science from National Yang Ming Chiao Tung University, advised by Prof. Ping-Chun Hsieh. In fall 2024 I was an exchange student at the University of Illinois Urbana-Champaign.


We propose BOFormer, a generalized deep Q-learning framework for Multi-Objective Bayesian Optimization (MOBO) via sequence modeling.