Grid-augmented vision: A simple yet effective approach for enhanced spatial understanding in multi-modal agents

Documenti analoghi

• SJTU:Spatial judgments in multimodal models towards unified segmentation through coordinate detection
  di: Chae, Joongwon, et al.
  Pubblicazione: (2024)
• Memory-SAM: Human-Prompt-Free Tongue Segmentation via Retrieval-to-Prompt
  di: Chae, Joongwon, et al.
  Pubblicazione: (2025)
• GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detection
  di: Chae, Joongwon, et al.
  Pubblicazione: (2026)
• StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection
  di: Chae, Joongwon, et al.
  Pubblicazione: (2026)
• LLaVAction: evaluating and training multi-modal large language models for action understanding
  di: Qi, Haozhe, et al.
  Pubblicazione: (2025)