Shenghao Fu's picture

Shenghao Fu

fushh7

·

AI & ML interests

None yet

Recent Activity

new activity about 6 hours ago

fushh7/ObjEmbed-4B:Add pipeline tag and improve model card

new activity about 6 hours ago

fushh7/ObjEmbed-2B:Add model card metadata and description

authored a paper about 21 hours ago

ObjEmbed: Towards Universal Multimodal Object Embeddings

View all activity

Organizations

Collections 2

Papers 11

arxiv:2602.01753

arxiv:2512.12309

arxiv:2512.10730

arxiv:2509.24786

models 13

fushh7/ObjEmbed-4B

Image Feature Extraction • 5B • Updated about 6 hours ago • 17

fushh7/ObjEmbed-2B

Image Feature Extraction • 2B • Updated about 6 hours ago • 15

fushh7/WeDetect

Zero-Shot Object Detection • Updated Dec 16, 2025 • 2

fushh7/WeDetect-Ref-2B

Zero-Shot Object Detection • 2B • Updated Dec 16, 2025 • 59

fushh7/WeDetect-Ref-4B

Zero-Shot Object Detection • 5B • Updated Dec 16, 2025 • 23

fushh7/llmdet_swin_large_hf

Zero-Shot Object Detection • 0.3B • Updated Apr 8, 2025 • 1.3k • 6

fushh7/llmdet_swin_base_hf

Zero-Shot Object Detection • 0.2B • Updated Apr 8, 2025 • 2

fushh7/llmdet_swin_tiny_hf

Zero-Shot Object Detection • 0.2B • Updated Apr 8, 2025 • 3.03k • 3

fushh7/ViSpeak-s3

Visual Question Answering • 8B • Updated Apr 7, 2025 • 4

fushh7/ViSpeak-s2

Visual Question Answering • 8B • Updated Apr 7, 2025 • 2

datasets 3

fushh7/eval_refcoco

Viewer • Updated Dec 16, 2025 • 19.2k • 43

fushh7/ViSpeak-Instruct

Preview • Updated Jul 14, 2025 • 14 • 1

fushh7/ViSpeak-Bench

Viewer • Updated Apr 12, 2025 • 901 • 12