Yanjun Wu

HLD: Approximate Hierarchical Linguistic Distribution Modeling for LLM-Generated Text Detection

Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction

Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaptation

AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework

KnowOS: Knowledge-driven Large Language Models for Operating System Kernel Tuning

SecTest-Eval: Can LLMs Verify Security Impacts of A Vulnerability?

Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning

EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization

SciPG: A New Benchmark and Approach for Layout-aware Scientific Poster Generation