10 papers
Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Kushal Raj Bhandari, Ling Yue, Ching-Yun Ko +4
Compact language models (LMs) reduce cost, latency, and deployment risk for tool agents. Yet MCP-style tool use requires more than isolated function calling: an agent must discover…
Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
Yu-Ang Lee, Ching-Yun Ko, Pin-Yu Chen +1
Low-Rank Adaptation (LoRA) is the prevailing approach for efficient large language model (LLM) fine-tuning. Building on this paradigm, recent studies have proposed alternative init…
Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models
Huzaifa Arif, Keerthiram Murugesan, Ching-Yun Ko +3
We propose patching for large language models (LLMs) like software versions, a lightweight and modular approach for addressing safety vulnerabilities. While vendors release improve…
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
Ling Yue, Kushal Raj Bhandari, Ching-Yun Ko +6
Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval,…
EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation
Jiahe Shi, Zhengqi Gao, Ching-Yun Ko +1
Recent advances in large language models (LLMs) have demonstrated significant potential in hardware design automation, particularly in using natural language to synthesize Register…
Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
Chen Xiong, Zhiyuan He, Pin-Yu Chen +2
Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, develope…