8 papers
STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal Perturbations
Yuhan Xie, Yuping Yan, Yunqi Zhao +2
Despite their strong performance in embodied tasks, recent Vision-Language-Action (VLA) models remain highly fragile under multimodal perturbations, where visual corruption and lin…
Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design
Yuchen Li, Handing Wang, Bing Xue +2
In the high-cost simulation-driven design domain, translating ambiguous design requirements into a mathematical optimization formulation is a bottleneck for optimizing product perf…
Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models
Jiangtao Liu, Zhaoxin Wang, Handing Wang +2
Text-to-Image (T2I) generation has advanced rapidly in recent years, but they also raise safety concerns due to the potential production of harmful content. In the practical deploy…
Overlooked Safety Vulnerability in LLMs: Malicious Intelligent Optimization Algorithm Request and its Jailbreak
Haoran Gu, Handing Wang, Yi Mei +2
The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the s…
One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models
Haoran Gu, Handing Wang, Yi Mei +2
Large Language Models (LLMs) have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research. However, they rema…
ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data
Haoran Gu, Handing Wang, Yi Mei +2
Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobj…