Shenghao Fu

fushh7

11 16 2

AI & ML interests

None yet

Recent Activity

upvoted a paper about 23 hours ago

3DCodeVerse: Exploring 3D Worlds as Code

upvoted a paper about 2 months ago

WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report

upvoted a paper 5 months ago

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

View all activity

Organizations

Collections 2

Papers 11

models 15

datasets 4

fushh7/ObjEmbed_training_data

Preview • Updated May 18 • 158 • 1

fushh7/eval_refcoco

Viewer • Updated Dec 16, 2025 • 19.2k • 139

fushh7/ViSpeak-Instruct

Preview • Updated Jul 14, 2025 • 589 • 1

fushh7/ViSpeak-Bench

Viewer • Updated Apr 12, 2025 • 901 • 102

Shenghao Fu

AI & ML interests

Recent Activity

Organizations

Collections 2

fushh7/ObjEmbed-2B

fushh7/ObjEmbed-4B

ObjEmbed: Towards Universal Multimodal Object Embeddings

fushh7/ObjEmbed_training_data

fushh7/WeDetect-Ref-4B

fushh7/WeDetect

fushh7/WeDetect-Ref-2B

WeDetect: Fast Open-Vocabulary Object Detection as Retrieval

fushh7/ObjEmbed-2B

fushh7/ObjEmbed-4B

ObjEmbed: Towards Universal Multimodal Object Embeddings

fushh7/ObjEmbed_training_data

fushh7/WeDetect-Ref-4B

fushh7/WeDetect

fushh7/WeDetect-Ref-2B

WeDetect: Fast Open-Vocabulary Object Detection as Retrieval

Papers 11

models 15

fushh7/WeDetect-Ref-4B-stage2

fushh7/WeDetect-Ref-2B-stage2

fushh7/ObjEmbed-4B

fushh7/ObjEmbed-2B

fushh7/WeDetect

fushh7/WeDetect-Ref-2B

fushh7/WeDetect-Ref-4B

fushh7/llmdet_swin_large_hf

fushh7/llmdet_swin_base_hf

fushh7/llmdet_swin_tiny_hf

datasets 4

fushh7/ObjEmbed_training_data

fushh7/eval_refcoco

fushh7/ViSpeak-Instruct

fushh7/ViSpeak-Bench

Shenghao Fu

AI & ML interests

Recent Activity

Organizations

Collections 2

Papers 11

models 15 Sort: Recently updated

datasets 4 Sort: Recently updated

models 15

datasets 4