Yuanbo Wen

GOOD: Decoding-Time Black-Box LLM Alignment

One for all: Zero-Shot Cross-Hardware Performance Modeling with LLMs for Tensor Program Tuning

MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions

QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code

GOOD: Decoding-Time Black-Box LLM Alignment

QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation

GOOD: Decoding-Time Black-Box LLM Alignment