GROUNDHOG: Grounding Large Language Models to Holistic Segmentation

Documenti analoghi

• World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models
  di: Ma, Ziqiao, et al.
  Pubblicazione: (2023)
• VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation
  di: Yu, Shoubin, et al.
  Pubblicazione: (2025)
• Multi-Object Hallucination in Vision-Language Models
  di: Chen, Xuweiyi, et al.
  Pubblicazione: (2024)
• DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences
  di: Huang, Yidong, et al.
  Pubblicazione: (2024)
• Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models
  di: Ma, Ziqiao, et al.
  Pubblicazione: (2023)