3 papers
eess.SY2026
Self-Evolving Learning for Embodied AI with Criticality Model
Linxuan He, Yuying Tian, Lingxiang Fan +5
Despite rapid advances in policy pretraining, embodied AI systems routinely plateau during task-specific finetuning. The root cause lies in how finetuning data are collected: the d…
eess.SY2025
Efficient Safety Verification of Autonomous Vehicles with Neural Network Operator
Lingxiang Fan, Linxuan He, Haoyuan Ji +1
When autonomous vehicles encounter untrained scenarios, ensuring safety hinges on effective safety verification to prevent accidents stemming from unexpected model decisions. Reach…
eess.SY2025
Towards provable probabilistic safety for scalable embodied AI systems
Linxuan He, Lingxiang Fan, Qing-Shan Jia +13
Embodied AI systems, comprising AI models and physical plants, are increasingly prevalent across various applications. Due to the rarity of system failures, ensuring their safety i…