4 papers
SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models
Zongrui Wang, Xiangyang Zhu, Sicheng Wang +13
Multimodal safety moderation requires distinguishing risks arising from visual content, user intent, and assistant behavior. Existing safeguards, however, are typically trained for…
H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models
Dingyi Rong, Yue Shi, Chaofan Ma +6
Large-scale manipulation data is essential for robot learning, yet collecting robot demonstrations remains expensive and difficult to scale. Meanwhile, abundant egocentric human ma…
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
Sicheng Wang, Xiangyang Zhu, Han Wang +6
Prior work has shown that fine-tuning large language models on malicious or incorrect outputs in narrow domains can induce broad misalignment and harmful behavior, a phenomenon kno…
Automated Safety Benchmarking: A Multi-agent Pipeline for LVLMs
Xiangyang Zhu, Yuan Tian, Zicheng Zhang +6
Large vision-language models (LVLMs) exhibit remarkable capabilities in cross-modal tasks but face significant safety challenges, which undermine their reliability in real-world ap…