3 citations · 4 across the 12 of their papers we have counts for
13 papers
Adaptive Co-Serving LLM Watermarking on Modern Inference Engines
Kieu Dang, Phung Lai, Ching-Yun Ko +1
Large language model (LLM) watermarking is important for ownership verification and intellectual property protection. However, existing approaches focus on algorithmic design while…
EvoFlux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Kushal Raj Bhandari, Ling Yue, Ching-Yun Ko +4
Small language models (1.5B-4B parameters) offer low-cost, low-latency tool use but often produce plausible plans that fail during execution due to unavailable tools, missing argum…
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,…
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…
vLLM Hook v0: A Plug-in for Programming Model Internals on vLLM
Ching-Yun Ko, Pin-Yu Chen
Modern artificial intelligence (AI) models are deployed on inference engines to optimize runtime efficiency and resource allocation, particularly for transformer-based large langua…
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…
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…
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…
Can Memory-Augmented Language Models Generalize on Reasoning-in-a-Haystack Tasks?
Payel Das, Ching-Yun Ko, Sihui Dai +3
Large language models often expose their brittleness in reasoning tasks, especially while executing long chains of reasoning over context. We propose MemReasoner, a new and simple…
STAR: Spectral Truncation and Rescale for Model Merging
Yu-Ang Lee, Ching-Yun Ko, Tejaswini Pedapati +3
Model merging is an efficient way of obtaining a multi-task model from several pretrained models without further fine-tuning, and it has gained attention in various domains, includ…
Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models
Chung-Ting Tsai, Ching-Yun Ko, I-Hsin Chung +2
The rapid advancement of generative models has introduced serious risks, including deepfake techniques for facial synthesis and editing. Traditional approaches rely on training cla…
Attention Tracker: Detecting Prompt Injection Attacks in LLMs
Kuo-Han Hung, Ching-Yun Ko, Ambrish Rawat +3
Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring origin…
Large Language Models can be Strong Self-Detoxifiers
Ching-Yun Ko, Pin-Yu Chen, Payel Das +6
Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external…