RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient Inference

Documenti analoghi

• DeeAD: Dynamic Early Exit of Vision-Language Action for Efficient Autonomous Driving
  di: HU, Haibo, et al.
  Pubblicazione: (2025)
• Retrieval-Augmented Generation for Natural Language Processing: A Survey
  di: Wu, Shangyu, et al.
  Pubblicazione: (2024)
• Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving
  di: Hu, Haibo, et al.
  Pubblicazione: (2025)
• AD-EE: Early Exiting for Fast and Reliable Vision-Language Models in Autonomous Driving
  di: Huang, Lianming, et al.
  Pubblicazione: (2025)
• ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion
  di: Wu, Shangyu, et al.
  Pubblicazione: (2024)