DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization

Documenti analoghi

• Grounding Sim-to-Real Generalization in Dexterous Manipulation: An Empirical Study with Vision-Language-Action Models
  di: Jin, Ruixing, et al.
  Pubblicazione: (2026)
• DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
  di: Zheng, Zihao, et al.
  Pubblicazione: (2026)
• DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation
  di: Yang, Zebin, et al.
  Pubblicazione: (2026)
• SwitchVLA: Execution-Aware Task Switching for Vision-Language-Action Models
  di: Li, Meng, et al.
  Pubblicazione: (2025)
• A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
  di: Zhai, Shaopeng, et al.
  Pubblicazione: (2025)