Tianheng Cheng's picture

Tianheng Cheng

wondervictor

·

https://github.com/wondervictor

AI & ML interests

Computer vision, visual perception, multimodal models

Organizations

New activity in ByteDance-Seed/Seed1.5-VL 2 months ago

运行错误

#14 opened 3 months ago by

Error Running it on space

#15 opened 2 months ago by

GregoryDelatolas

New activity in ByteDance-Seed/Seed1.5-VL 3 months ago

Fix layout requested by https://huggingface.co/spaces/ByteDance-Seed/Seed1.5-VL/discussions/9#682f06bfcc42cf9552def4ee

#13 opened 3 months ago by

make the chat window taller

#9 opened 3 months ago by

Describe the image in detail, composition, technique, color

#6 opened 3 months ago by

test

#4 opened 3 months ago by

MultiModalityCausalLM

when will release weights?

#3 opened 3 months ago by

Fix screenshot case

#2 opened 3 months ago by

fix png

#1 opened 3 months ago by

commented a paper 3 months ago

Seed1.5-VL Technical Report

Paper • 2505.07062 • Published May 11 • 150 •

commented a paper 5 months ago

GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding

Paper • 2503.10596 • Published Mar 13 • 18 •

commented a paper 11 months ago

ControlAR: Controllable Image Generation with Autoregressive Models

Paper • 2410.02705 • Published Oct 3, 2024 • 11 •

New activity in wondervictor/evf-sam2 about 1 year ago

Compile CUDA kernels (SAM2) on HuggingFace Spaces (ZeroGPU)

#1 opened about 1 year ago by

New activity in wondervictor/YOLO-World-Image about 1 year ago

Apply for community grant: Academic project (gpu)

#1 opened about 1 year ago by

New activity in wondervictor/evf-sam about 1 year ago

Apply for community grant: Personal project (gpu)

#1 opened about 1 year ago by

commented 2 papers about 1 year ago

EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model

Paper • 2406.20076 • Published Jun 28, 2024 • 10 •

EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model

Paper • 2406.20076 • Published Jun 28, 2024 • 10 •