Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

Documenti analoghi

• Model-Based Runtime Monitoring with Interactive Imitation Learning
  di: Liu, Huihan, et al.
  Pubblicazione: (2023)
• DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
  di: Kim, Changyeon, et al.
  Pubblicazione: (2025)
• Verifier-free Test-Time Sampling for Vision Language Action Models
  di: Jang, Suhyeok, et al.
  Pubblicazione: (2025)
• PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning
  di: Gao, Tian, et al.
  Pubblicazione: (2024)
• SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning
  di: Zhang, Yu, et al.
  Pubblicazione: (2025)