arxiv:2404.07987
Ming Li
limingcv
AI & ML interests
Computer Vision, AIGC, VLM/LLM
Recent Activity
upvoted
a
paper
3 days ago
Cosmos World Foundation Model Platform for Physical AI
new activity
about 1 month ago
THUDM/CogVideoX1.5-5B-I2V:Could you provide the image used for the demo in README?
upvoted
a
paper
about 2 months ago
Enhancing the Reasoning Ability of Multimodal Large Language Models via
Mixed Preference Optimization
Organizations
datasets
10
limingcv/MultiGen-20M_train
Viewer
•
Updated
•
2.81M
•
3.52k
•
2
limingcv/JourneyDB_part2
Viewer
•
Updated
•
2.08M
•
1.33k
limingcv/JourneyDB_part1
Viewer
•
Updated
•
2.08M
•
965
limingcv/HumanArt
Viewer
•
Updated
•
83.5k
•
4
limingcv/MultiGen-20M_canny_eval
Viewer
•
Updated
•
5.5k
•
106
•
1
limingcv/MultiGen-20M_depth_eval
Viewer
•
Updated
•
5k
•
221
•
1
limingcv/Captioned_COCOPose
Viewer
•
Updated
•
66.8k
•
4
limingcv/Captioned_COCOStuff
Viewer
•
Updated
•
123k
•
618
limingcv/Captioned_ADE20K
Viewer
•
Updated
•
22.2k
•
273
•
2
limingcv/MultiGen-20M_depth
Viewer
•
Updated
•
2.81M
•
2.72k
•
3