collaborators

19 papers

cs.CR2026

D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting

Huanli Gong, Zhipeng Wei, Yu Fu +4

Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they exploit feedback from auxiliary judge models to iteratively refine prompts towa…

cs.LG2026

Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation

Yu Fu, Longxuan Yu, Haz Sameen Shahgir +4

Safety alignment often improves robustness to harmful queries at the cost of reasoning ability, a tradeoff known as the safety tax. A common cause is distributional mismatch: super…

cs.CL2026

Do Reasoning LLMs Refuse What They Infer in Long Contexts?

Yu Fu, Haz Sameen Shahgir, Huanli Gong +3

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it als…

cs.LG2026

Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching

Aditi Gupta, Soon Hoe Lim, Annan Yu +1

Flow matching models generate samples by numerically integrating a learned velocity field, with each integration step requiring a neural network evaluation. Fast generation therefo…

cs.CR2026

MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks

Xinkai Zhang, Zhipeng Wei, Huanli Gong +4

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can g…

cs.LG2026

Continuity Laws for Sequential Models

Annan Yu, Dongwei Lyu, N. Benjamin Erichson

Inductive biases influence the behavior and performance of sequential models. In this work, we study an underexplored inductive bias in sequential modeling: continuity in time. We…