Zhejian Peng
Research / Project
Papers and systems.
MatrAIx
8.3 billion persona agents for testing AI and products.
FlashInfer deterministic top-k
Added a deterministic mode to top_k_renorm_probs in FlashInfer, the GPU kernel library for LLM serving.
Difficulty-aware looped transformer
A training and inference setup that spends more loops on harder problems and fewer on easy ones.
Fresh in-store production
Probabilistic forecast plus optimization for what a store should bake and stock. US patent 2022/0318709 A1.
