wujing

edatai's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 9 days ago

SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models

Paper • 2608.01899 • Published 19 days ago • 1

updated a dataset 18 days ago

edatai/spatiolm-depth

Updated 18 days ago • 184

published a dataset 18 days ago

edatai/spatiolm-depth

Updated 18 days ago • 184

updated a collection 18 days ago

SpatioLM

Collection

SpatioLM is a parameter-efficient framework for improving spatial intelligence in vision-language models (VLMs). It introduces a plug-and-play spatio- • 5 items • Updated 18 days ago • 1

updated 5 models 18 days ago

xiaomi-research/SpatioLM-Action-VLA0

Image-Text-to-Text • 2B • Updated 18 days ago • 24

xiaomi-research/SpatioLM-Perception-SenseNovaSI

Image-Text-to-Text • 8B • Updated 18 days ago • 29

xiaomi-research/SpatioLM-Perception-InternVL3.5

Image-Text-to-Text • 9B • Updated 18 days ago • 36

xiaomi-research/SpatioLM-Understanding-SenseNovaSI

Image-Text-to-Text • 8B • Updated 18 days ago • 40

xiaomi-research/SpatioLM-Understanding-InternVL3.5

Image-Text-to-Text • 9B • Updated 18 days ago • 67

published 5 models 18 days ago

xiaomi-research/SpatioLM-Action-VLA0

Image-Text-to-Text • 2B • Updated 18 days ago • 24

xiaomi-research/SpatioLM-Perception-SenseNovaSI

Image-Text-to-Text • 8B • Updated 18 days ago • 29

xiaomi-research/SpatioLM-Perception-InternVL3.5

Image-Text-to-Text • 9B • Updated 18 days ago • 36

xiaomi-research/SpatioLM-Understanding-SenseNovaSI

Image-Text-to-Text • 8B • Updated 18 days ago • 40

xiaomi-research/SpatioLM-Understanding-InternVL3.5

Image-Text-to-Text • 9B • Updated 18 days ago • 67

New activity in discord-community/WelcomeBot over 1 year ago

test

114

#1 opened over 1 year ago by

adamm-hf