FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation

Documenti analoghi

• Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
  di: Zhan, Yufei, et al.
  Pubblicazione: (2025)
• Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring
  di: Zhan, Yufei, et al.
  Pubblicazione: (2024)
• GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models
  di: Zheng, Shurong, et al.
  Pubblicazione: (2026)
• TraceVision: Trajectory-Aware Vision-Language Model for Human-Like Spatial Understanding
  di: Yang, Fan, et al.
  Pubblicazione: (2026)
• Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models
  di: Zhan, Yufei, et al.
  Pubblicazione: (2024)