6 papers
PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails
Mingyang Song, Luxin Xu, Haoyu Sun +3
Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image. Real deployments are different: t…
-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Haoran Zhang, Luxin Xu, Zhilin Wang +11
The rise of personal assistant agents, e.g., OpenClaw, highlights the growing potential of large language models to support users across everyday life and work. A core challenge in…
CoTZero: Annotation-Free Human-Like Vision Reasoning via Hierarchical Synthetic CoT
Chengyi Du, Yazhe Niu, Dazhong Shen +1
Recent advances in vision-language models (VLMs) have markedly improved image-text alignment, yet they still fall short of human-like visual reasoning. A key limitation is that man…
AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
Mingyang Song, Haoyu Sun, Jiawei Gu +4
When humans face problems beyond their immediate capabilities, they rely on tools, providing a promising paradigm for improving visual reasoning in multimodal large language models…
X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability
Xiaoya Lu, Dongrui Liu, Yi Yu +2
Despite the rapid development of safety alignment techniques for LLMs, defending against multi-turn jailbreaks is still a challenging task. In this paper, we conduct a comprehensiv…
RxSafeBench: Identifying Medication Safety Issues of Large Language Models in Simulated Consultation
Jiahao Zhao, Luxin Xu, Minghuan Tan +4
Numerous medical systems powered by Large Language Models (LLMs) have achieved remarkable progress in diverse healthcare tasks. However, research on their medication safety remains…