3 papers
cs.SE2025
GraphCue for SDN Configuration Code Synthesis
Haomin Qi, Fengfei Yu, Chengbo Huang
We present GraphCue, a topology-grounded retrieval and agent-in-the-loop framework for automated SDN configuration. Each case is abstracted into a JSON graph and embedded using a l…
cs.CL2025
Governance-Aware Hybrid Fine-Tuning for Multilingual Large Language Models
Haomin Qi, Chengbo Huang, Zihan Dai +1
We present a governance-aware hybrid fine-tuning framework for multilingual, low-resource adaptation of large language models. The core algorithm combines gradient-aligned low-rank…
cs.CL2025
Hybrid and Unitary PEFT for Resource-Efficient Large Language Models
Haomin Qi, Zihan Dai, Chengbo Huang
Fine-tuning large language models (LLMs) remains a computational bottleneck due to their scale and memory demands. This paper presents a comprehensive evaluation of parameter-effic…