500AI
← People

Zhitong Xiong

  • Multimodal AI

Selected work

5
  1. DOFA-CLIP: Multimodal Vision-Language Foundation Models for Earth ObservationFirst author · 2025
  2. Neural Plasticity-Inspired Multimodal Foundation Model for Earth ObservationFirst author · 2024
  3. Panopticon: Advancing Any-Sensor Foundation Models for Earth ObservationContributor · 2025
  4. EarthNets: Empowering AI in Earth ObservationFirst author · 2022
  5. ChatEarthNet: A Global-Scale Image-Text Dataset Empowering Vision-Language Geo-Foundation ModelsCreator · 2024