Mengjie Zhang

Decoding One Safety Trigger Token for Balancing Safety and Usability in Large Language Models

D-STT, a simple yet effective defense algorithm that identifies and explicitly decodes safety trigger tokens of the given safety-aligned LLM to activate the model's learned safety patterns, effectively preserves model usability by introducing minimum intervention in the decoding process.

Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI

This paper presents a systematic refactoring approach using Claude agentic AI on real-world project-scheduling workloads in a high-performance computing (HPC) environment, where the agent identifies bottlenecks, implements targeted optimizations, and evaluates their effects, while the researcher retains final control.

ComGPL: Genetic Programming for Learning Traffic Signal Control Policies With Intersection Communications

Guiding Large Language Models with Genetic Programming-Evolved Heuristic Knowledge for Dynamic Multi-Mode Project Scheduling

This work transfers knowledge in the reverse direction, using knowledge extracted from high-quality GP rules to guide an online LLM decision maker, and injects it through Feature Selection, Feature Hint, Rule Reference, and Rule Follow.