LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics

Documenti analoghi

• Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots
  di: Williams, Justin, et al.
  Pubblicazione: (2025)
• LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception
  di: williams, Justin, et al.
  Pubblicazione: (2026)
• EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices
  di: Liu, Mengyun, et al.
  Pubblicazione: (2026)
• ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Control
  di: Chen, Lingling, et al.
  Pubblicazione: (2026)
• EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control
  di: Zhang, Chushan, et al.
  Pubblicazione: (2026)