Tianheng Cheng's picture

Tianheng Cheng

wondervictor

·

https://github.com/wondervictor

AI & ML interests

Computer vision, visual perception, multimodal models

Recent Activity

authored a paper 8 days ago

Mixture-of-Depths Attention

upvoted a paper 29 days ago

Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning

new activity 10 months ago

ByteDance-Seed/Seed1.5-VL:运行错误

View all activity

Organizations

liked a model 10 months ago

ByteDance-Seed/BAGEL-7B-MoT

Any-to-Any • 15B • Updated Jan 9 • 7.86k • 1.18k

liked a Space 11 months ago

Seed1.5 VL

Seed1.5-VL API Demo

liked 5 Spaces over 1 year ago

IC Light V2-Vary

Execute custom code from environment variable

ControlAR-XL

Controllable Autoregressive Image Generation

Mask-Adapter-SAM2

InstantStyle

Style-Preserving Text-to-Image Generation

CSGO

Content-Style Composition (GoGoGo)

liked a model over 1 year ago

wondervictor/ControlAR

Updated Dec 11, 2024 • 3

liked 5 Spaces over 1 year ago

Stable Diffusion 3.5 Large

Generate images with SD3.5

EVF-SAM-2

Segment objects in images and videos using text prompts

YOLO-World-Image

Stable Diffusion 3 Medium

Generate images from text prompts

EVF-SAM

liked a dataset almost 2 years ago

openbmb/llava_zh

Viewer • Updated Jul 17, 2023 • 158k • 30 • 21

liked a model almost 2 years ago

google/siglip-so400m-patch14-384

Zero-Shot Image Classification • 0.9B • Updated Sep 26, 2024 • 2.71M • 664

liked a dataset almost 2 years ago

LooksJuicy/ruozhiba

Viewer • Updated Apr 9, 2024 • 1.5k • 186 • 316

liked 2 Spaces about 2 years ago

YOLO-World + EfficientSAM

Detect and segment objects in images or videos

YOLO World

Detect objects in images or videos

liked a model over 2 years ago

microsoft/phi-2

Text Generation • 3B • Updated Dec 8, 2025 • 1.76M • 3.43k