Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features

Documenti analoghi

• ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models
  di: Lee, Jewon, et al.
  Pubblicazione: (2025)
• Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods
  di: Kim, Bo-Kyeong, et al.
  Pubblicazione: (2024)
• Assessing the Answerability of Queries in Retrieval-Augmented Code Generation
  di: Kim, Geonmin, et al.
  Pubblicazione: (2024)
• LLaMA Pro: Progressive LLaMA with Block Expansion
  di: Wu, Chengyue, et al.
  Pubblicazione: (2024)
• Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model
  di: Kim, Dongki, et al.
  Pubblicazione: (2025)