HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling

Documenti analoghi

• E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMs
  di: Liu, Xianjie, et al.
  Pubblicazione: (2026)
• Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs
  di: Li, Xudong, et al.
  Pubblicazione: (2025)
• HiLM-D: Enhancing MLLMs with Multi-Scale High-Resolution Details for Autonomous Driving
  di: Ding, Xinpeng, et al.
  Pubblicazione: (2023)
• Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning
  di: Zou, Yixiong, et al.
  Pubblicazione: (2024)
• Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement
  di: Yu, Xuan, et al.
  Pubblicazione: (2025)