Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations

Documenti analoghi

• JailWAM: Jailbreaking World Action Models in Robot Control
  di: Liu, Hanqing, et al.
  Pubblicazione: (2026)
• VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
  di: Huang, Alex S., et al.
  Pubblicazione: (2026)
• Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
  di: Long, Jiahuan, et al.
  Pubblicazione: (2025)
• RotVLA: Rotational Latent Action for Vision-Language-Action Model
  di: Li, Qiwei, et al.
  Pubblicazione: (2026)
• RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models
  di: Luo, Jingzhou, et al.
  Pubblicazione: (2026)