Xuanke Shi

shixuanke's activity

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

upvoted a paper 10 days ago

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published 11 days ago • 68

updated a model 10 days ago

sensenova/ConsistCompose-BAGEL-7B-MoT

Updated 10 days ago • 33 • 7

upvoted a collection 14 days ago

SenseNova-U1

Collection

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-Unify Architecture • 4 items • Updated about 18 hours ago • 43

published a model 14 days ago

sensenova/SenseNova-U1-8B-MoT

Any-to-Any • 18B • Updated about 21 hours ago • 2.72k • 192

liked a dataset 15 days ago

shixuanke/ConsistCompose3M

Viewer • Updated Feb 25 • 11.3M • 728 • 3

commented a paper 15 days ago

MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings

Paper • 2604.19902 • Published 17 days ago • 2 •

2

liked a Space 25 days ago

Running on Zero

Agents

38

RefineAnything

🖼

38

Refine selected image area with a text prompt

upvoted a paper 27 days ago

Beyond Language Modeling: An Exploration of Multimodal Pretraining

Paper • 2603.03276 • Published Mar 3 • 104

updated a dataset about 1 month ago

sensenova/ConsistCompose3M

Viewer • Updated Mar 31 • 11.3M • 23 • 8

upvoted an article about 2 months ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

Mar 5

•

153

liked a dataset 2 months ago

sensenova/ConsistCompose3M

Viewer • Updated Mar 31 • 11.3M • 23 • 8

authored 2 papers 2 months ago

Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

Paper • 2508.13142 • Published Aug 18, 2025 • 34

ConsistCompose: Unified Multimodal Layout Control for Image Composition

Paper • 2511.18333 • Published Nov 23, 2025 • 5

liked a model 2 months ago

sensenova/ConsistCompose-BAGEL-7B-MoT

Updated 10 days ago • 33 • 7

published a model 2 months ago

sensenova/ConsistCompose-BAGEL-7B-MoT

Updated 10 days ago • 33 • 7

updated a collection 2 months ago

MLLM_tools

Collection

1 item • Updated Feb 25

published a dataset 2 months ago

sensenova/ConsistCompose3M

Viewer • Updated Mar 31 • 11.3M • 23 • 8

commented a paper 3 months ago

ConsistCompose: Unified Multimodal Layout Control for Image Composition

Paper • 2511.18333 • Published Nov 23, 2025 • 5 •

1

upvoted a paper 5 months ago

ConsistCompose: Unified Multimodal Layout Control for Image Composition

Paper • 2511.18333 • Published Nov 23, 2025 • 5

authored a paper 5 months ago

Scaling Spatial Intelligence with Multimodal Foundation Models

Paper • 2511.13719 • Published Nov 17, 2025 • 49