SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions

Documenti analoghi

• TEn-CATG:Text-Enriched Audio-Visual Video Parsing with Multi-Scale Category-Aware Temporal Graph
  di: Chen, Yaru, et al.
  Pubblicazione: (2025)
• Visual Semantic Description Generation with MLLMs for Image-Text Matching
  di: Chen, Junyu, et al.
  Pubblicazione: (2025)
• Quizzard@INOVA Challenge 2025 -- Track A: Plug-and-Play Technique in Interleaved Multi-Image Model
  di: Cuong, Dinh Viet, et al.
  Pubblicazione: (2025)
• Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation
  di: Yang, Sicheng, et al.
  Pubblicazione: (2025)
• MultiSoundGen: Video-to-Audio Generation for Multi-Event Scenarios via SlowFast Contrastive Audio-Visual Pretraining and Direct Preference Optimization
  di: Yang, Jianxuan, et al.
  Pubblicazione: (2025)