ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference

Documenti analoghi

• Prototype-Based Test-Time Adaptation of Vision-Language Models
  di: Huang, Zhaohong, et al.
  Pubblicazione: (2026)
• GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
  di: Huang, Zhaohong, et al.
  Pubblicazione: (2025)
• VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
  di: Jiang, Pengfei, et al.
  Pubblicazione: (2025)
• DS$^2$Net: Detail-Semantic Deep Supervision Network for Medical Image Segmentation
  di: Huang, Zhaohong, et al.
  Pubblicazione: (2025)
• MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning
  di: Ma, Yiwei, et al.
  Pubblicazione: (2025)