Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding

Documenti analoghi

• A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions
  di: Liu, Daizong, et al.
  Pubblicazione: (2024)
• Joint Top-Down and Bottom-Up Frameworks for 3D Visual Grounding
  di: Liu, Yang, et al.
  Pubblicazione: (2024)
• HandMCM: Multi-modal Point Cloud-based Correspondence State Space Model for 3D Hand Pose Estimation
  di: Cheng, Wencan, et al.
  Pubblicazione: (2026)
• 3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding
  di: Li, Zeju, et al.
  Pubblicazione: (2024)
• From Part to Whole: 3D Generative World Model with an Adaptive Structural Hierarchy
  di: Du, Bi'an, et al.
  Pubblicazione: (2026)