[ICLR 2025 Spotlight] OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text https://github.com/OpenGVLab/OmniCorpus
Qingyun Li
Qingyun
AI & ML interests
Object Detection, Remote Sensing
Organizations
[Remote Sensing 2026] Co-Training Vision Language Models for Remote Sensing Multi-task Learning. https://github.com/VisionXLab/RSCoVLM
-
Co-Training Vision Language Models for Remote Sensing Multi-task Learning
Paper • 2511.21272 • Published -
Qingyun/remote-sensing-sft-data
Preview • Updated • 1.99k • 4 -
Qingyun/RSCoVLM-7B-2512
Image-Text-to-Text • 8B • Updated • 64 • 1 -
Qingyun/RSCoVLM-det-7B-2512
Image-Text-to-Text • 8B • Updated • 20
[ICLR 2025 Spotlight] OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text https://github.com/OpenGVLab/OmniCorpus
[Remote Sensing 2026] Co-Training Vision Language Models for Remote Sensing Multi-task Learning. https://github.com/VisionXLab/RSCoVLM
-
Co-Training Vision Language Models for Remote Sensing Multi-task Learning
Paper • 2511.21272 • Published -
Qingyun/remote-sensing-sft-data
Preview • Updated • 1.99k • 4 -
Qingyun/RSCoVLM-7B-2512
Image-Text-to-Text • 8B • Updated • 64 • 1 -
Qingyun/RSCoVLM-det-7B-2512
Image-Text-to-Text • 8B • Updated • 20
models 7
Qingyun/RSCoVLM-det-7B-2512
Image-Text-to-Text • 8B • Updated • 20
Qingyun/RSCoVLM-7B-2512
Image-Text-to-Text • 8B • Updated • 64 • 1
Qingyun/RSCoVLM_ckpts
Updated
Qingyun/OmniCorpus-InternVL
8B • Updated • 5 • 6
Qingyun/Florence-2-models-lmmrotate
Image-Text-to-Text • Updated • 2
Qingyun/Florence-2-large-DOTA-v1.0-lmmrotate
Image-Text-to-Text • 0.9B • Updated • 27 • 3
Qingyun/RSCoTr
Updated
datasets 6
Qingyun/remote-sensing-sft-data
Preview • Updated • 1.99k • 4
Qingyun/transfer
Updated • 16
Qingyun/RSCoVLM_ckpts
Viewer • Updated • 1.2M • 13
Qingyun/lmmrotate-sft-data
Updated • 24 • 2
Qingyun/omnicorpus-cc-npmi
Viewer • Updated • 500k • 33
Qingyun/llava_v1_5_fewshot_sft
Preview • Updated • 13 • 2