Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations

Documenti analoghi

• CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos
  di: Zhang, Chubin, et al.
  Pubblicazione: (2026)
• Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
  di: Lin, Tao, et al.
  Pubblicazione: (2025)
• Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Driving
  di: Gopalkrishnan, Akshay, et al.
  Pubblicazione: (2024)
• F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions
  di: Lv, Qi, et al.
  Pubblicazione: (2025)
• MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesis
  di: Zhang, Hengyuan, et al.
  Pubblicazione: (2025)