Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

Ähnliche Einträge

• Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
  von: Huang, Wenxuan, et al.
  Veröffentlicht: (2025)
• LLaVA-RadZ: Can Multimodal Large Language Models Effectively Tackle Zero-shot Radiology Recognition?
  von: Li, Bangyan, et al.
  Veröffentlicht: (2025)
• Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding
  von: Huo, Mingxiao, et al.
  Veröffentlicht: (2025)
• LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
  von: Zhang, Shaolei, et al.
  Veröffentlicht: (2025)
• LLaVA-Critic: Learning to Evaluate Multimodal Models
  von: Xiong, Tianyi, et al.
  Veröffentlicht: (2024)