Tianheng Cheng

wondervictor

·

https://github.com/wondervictor

AI & ML interests

Computer vision, visual perception, multimodal models

Recent Activity

updated a model about 2 months ago

wondervictor/ControlAR

authored a paper 7 months ago

Mixture-of-Depths Attention

upvoted a paper 7 months ago

Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning

View all activity

Organizations

wondervictor 's Spaces 5

YOLO-World-Image

ControlAR-XL

Controllable Autoregressive Image Generation

Mask-Adapter-SAM2

EVF-SAM-2

Segment objects in images and videos using text prompts

EVF-SAM