Xinjie

Xinjie-Q's activity

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

updated a model 5 days ago

microsoft/Mage-VL

Image-Text-to-Text • 5B • Updated 5 days ago • 482k • 343

New activity in microsoft/Mage-VL 9 days ago

Fix <|image_pad|> misalignment when images= and videos= coexist

#3 opened 11 days ago by

kcz358

New activity in microsoft/Mage-VL 17 days ago

docs: add install-free Transformers usage section

#2 opened 17 days ago by

kcz358

Demo for this model on Spaces

👀 1

2

#1 opened 20 days ago by

multimodalart

upvoted a paper 17 days ago

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Paper • 2607.24904 • Published 19 days ago • 37

authored a paper 18 days ago

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paper • 2607.19064 • Published 25 days ago • 77

updated a model 19 days ago

microsoft/Mage-ViT

Image Feature Extraction • 0.3B • Updated 19 days ago • 8.04k • 30

liked 2 models 20 days ago

microsoft/Mage-ViT

Image Feature Extraction • 0.3B • Updated 19 days ago • 8.04k • 30

microsoft/Mage-VL

Image-Text-to-Text • 5B • Updated 5 days ago • 482k • 343

published 2 models 20 days ago

microsoft/Mage-VL

Image-Text-to-Text • 5B • Updated 5 days ago • 482k • 343

microsoft/Mage-ViT

Image Feature Extraction • 0.3B • Updated 19 days ago • 8.04k • 30

updated a collection 20 days ago

Mage

Collection

A family of lightweight multimodal models, including understanding and generation. • 8 items • Updated 20 days ago • 28

upvoted a collection 20 days ago

Mage

Collection

A family of lightweight multimodal models, including understanding and generation. • 8 items • Updated 20 days ago • 28

updated a collection 21 days ago

Mage

Collection

A family of lightweight multimodal models, including understanding and generation. • 8 items • Updated 20 days ago • 28

New activity in microsoft/mage-flow 22 days ago

Minor pipeline cleanup

1

#3 opened 22 days ago by

Xinjie-Q

Add quality model option to unified Space demo

1

#1 opened 23 days ago by

Xinjie-Q

Add quality model option and streamline blocked-content handling

#4 opened 22 days ago by

Xinjie-Q

upvoted 2 papers 24 days ago

SciForma: Structure-Faithful Generation of Scientific Diagrams

Paper • 2607.18091 • Published 26 days ago • 24

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paper • 2607.19064 • Published 25 days ago • 77

submitted a paper to Daily Papers 24 days ago

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paper • 2607.19064 • Published 25 days ago • 77