collaborators

7 papers

cs.CL2026

EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion

Ruijie Jian, Benlei Cui, Ting Ma +8

Existing evaluations of harmful content detection rely predominantly on static benchmarks, which struggle to reflect the interactive adversarial ecosystem of real-world content pla…

cs.CL2026

Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety

Ting Ma, Xiufeng Huang, Benlei Cui +43

As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safet…

cs.CV2026

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

Shikai Qiu, Xiaowen Xu, Benlei Cui +55

General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI s…

cs.CL2026

Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach

Zhihao Lin, Ziqi Zhu, Hao Huang +2

Literary translation poses unique challenges due to the scarcity of high-quality annotated data and the need to balance expression fluency with literary effect. We present a multi-…

cs.CR2026

LoopTrap: Termination Poisoning Attacks on LLM Agents

Huiyu Xu, Zhibo Wang, Wenhui Zhang +4

Modern LLM agents solve complex tasks by operating in iterative execution loops, where they repeatedly reason, act, and self-evaluate progress to determine when a task is complete.…

cs.CL2026

GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking

Ziqi Zhu, Adithya Suresh, Tomal Deb +1

Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models (LLMs) struggle despite thei…