collaborators

7 papers

cs.CL2026

Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs

Tung-Ling Li, Jiale Huang, Lee-Chi Wang +1

Merging a LoRA adapter into its base model is standard deployment practice: it removes the runtime adapter's per-forward overhead and leaves a single standalone checkpoint any serv…

cs.CL2026

Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment

Tung-Ling Li, Hongliang Liu, Yuhao Wu

Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable. We identify and test a central structural mechanism: BPE tokenization f…

cs.CR2026

The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills

Hongliang Liu, Yuhao Wu, Tung-Ling Li

AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from marketplaces and other agents. Gov…

cs.CR2026

Behavioral Integrity Verification for AI Agent Skills

Yuhao Wu, Tung-Ling Li, Hongliang Liu

Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution. Existing safety work catches mal…

cs.CL2026

Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs

Hongliang Liu, Tung-Ling Li, Yuhao Wu

Perturbation probing generates task-specific causal hypotheses for FFN neurons in large language models using two forward passes per prompt and no backpropagation, followed by a on…

cs.LG2025

AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens

Tung-Ling Li, Yuhao Wu, Hongliang Liu

LLM-as-a-Judge systems supply the reward signal in modern RLHF and RLVR pipelines, but their binary verdict reduces to a single linear readout F_gap on one hidden state. We show th…