collaborators

14 papers

cs.LG2026

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment

Changyue Li, Jiaming He, Youliang Yuan +4

Fine-Tuning-as-a-Service (FTaaS) platforms let users train large language models (LLMs) on customized tasks, but this pipeline could erode models' safety alignment. In practice, se…

cs.CV2026

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation

Changyue Li, Jiaying Li, Youliang Yuan +3

Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-A…

cs.CL2026

PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning

Yusong Zhao, Yuejin Xie, Youliang Yuan +4

Between the first visible sign of danger and the moment an accident occurs, there is often a window where intervention remains possible. Video-capable multimodal large language mod…

cs.CV2026

Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs

Jen-Tse Huang, Dasen Dai, Jen-Yuan Huang +7

Humans develop perception through a bottom-up hierarchy: from basic primitives and Gestalt principles to high-level semantics. In contrast, current Multimodal Large Language Models…

cs.CL2026

SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs

Sihang Zhao, Kangrui Yu, Youliang Yuan +2

Large Language Models (LLMs) have been widely explored in educational scenarios. We identify a critical vulnerability in current educational LLMs, pedagogical jailbreaks, where stu…

cs.CL2026

Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards

Youliang Yuan, Qiuyang Mang, Jingbang Chen +7

In this paper, we observe that current models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning ability. This is evidenced by a high…