FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers

Documenti analoghi

• Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding
  di: Zhang, Renshan, et al.
  Pubblicazione: (2024)
• MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models
  di: Shen, Leyang, et al.
  Pubblicazione: (2024)
• Curriculum Coarse-to-Fine Selection for High-IPC Dataset Distillation
  di: Chen, Yanda, et al.
  Pubblicazione: (2025)
• PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning
  di: Lyu, Yibo, et al.
  Pubblicazione: (2025)
• PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
  di: Lyu, Yibo, et al.
  Pubblicazione: (2026)