🤝 Open to Collab

Runjia Li PRO

liguang0115

6 24 19

AI & ML interests

None yet

Recent Activity

upvoted a paper 23 days ago

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

liked a dataset about 2 months ago

Syn4D/Syn4D

upvoted a paper 2 months ago

Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories

View all activity

Organizations

None yet

liked a dataset about 2 months ago

Syn4D/Syn4D

Updated 30 days ago • 67.1k • 20

liked a dataset 3 months ago

liguang0115/EgoEdit

Viewer • Updated Mar 18 • 37.3k • 199 • 6

liked a model 6 months ago

alibaba-pai/Wan2.2-Fun-5B-Control-Camera

Image-to-Video • Updated Dec 11, 2025 • 256 • 5

liked a model 9 months ago

krea/krea-realtime-video

Text-to-Video • 14B • Updated Nov 14, 2025 • 918 • 291

liked a Space 12 months ago

Qwen Image Edit

✒

860

Edit images using natural language instructions

liked a model about 1 year ago

facebook/dinov3-vitb16-pretrain-lvd1689m

Image Feature Extraction • 85.7M • Updated Aug 19, 2025 • 586k • 238

liked 2 Spaces about 1 year ago

Qwen Image

🖼

926

Generate high-quality images from text prompts

HaWoR

🚀

liked a model about 1 year ago

liguang0115/vmem

Updated Jun 24, 2025 • 5

liked 5 Spaces about 1 year ago

SAM2 Video Predictor

🔥

Segment and track objects in videos

WiLoR

🚀

Reconstruct 3D hands from images

FLUX.1 Dev Inpainting Model Beta GPU

🏆

265

Edit images with AI-driven inpainting using text prompts

V-MEM

⚡

Explore 3D Scenes by Navigating Uploaded Images

Frame Interpolation

🐢

Generate smooth video between two images

liked 2 Spaces over 1 year ago

CLIP as RNN

🔥

TRELLIS

🏢

4.78k

Scalable and Versatile 3D Generation from images

liked a model over 1 year ago

microsoft/wham

Updated Dec 17, 2025 • 341 • 272

liked a dataset almost 2 years ago

ShapeNet/ShapeSplatsV1

Updated Sep 5, 2024 • 133 • 44

liked a Space almost 2 years ago

MotionCtrl SVD

📉

130