3 papers
eess.SY2026
Policy-Level Recursive Self-Improvement for Embodied AI with a Criticality World Model
Linxuan He, Yuying Tian, Lingxiang Fan +5
Despite advances in policy pretraining, embodied AI systems can plateau during task-specific fine-tuning as uniform scenario collection encounters fewer of the remaining failures.…
cs.RO2026
DC-WAM: Dynamic-Centric Visual Supervision and Reasoning for World-Action Models
Haoyuan Ji, Lingxiang Fan, Shang Su +4
World-Action Models (WAMs) augment robot policies with future visual prediction, but it remains unclear what the visual modality should learn for control. While photorealistic futu…
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…