collaborators

11 papers

cs.CL2026

The Cold-Start Safety Gap in LLM Agents

Chung-En Sun, Linbo Liu, Tsui-Wei Weng

Are tool-calling LLM agents equally safe throughout a conversation? We discover they are not: agents are most vulnerable at the very start of a session and become substantially saf…

cs.CL2026

LLM Agents Already Know When to Call Tools -- Even Without Reasoning

Chung-En Sun, Linbo Liu, Ge Yan +2

Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark…

cs.CL2026

Steer2Edit: From Activation Steering to Component-Level Editing

Chung-En Sun, Ge Yan, Zimo Wang +1

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation…

cs.LG2026

Distance Marching for Generative Modeling

Zimo Wang, Ishit Mehta, Haolin Lu +4

Time-unconditional generative models learn time-independent denoising vector fields. But without time conditioning, the same noisy input may correspond to multiple noise levels and…

cs.AI2025

ReflCtrl: Controlling LLM Reflection via Representation Engineering

Ge Yan, Chung-En Sun, Tsui-Wei +1

Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A di…

cs.CL2025

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities

Chung-En Sun, Xiaodong Liu, Weiwei Yang +5

Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful quer…