Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval
Kong
friedrichor
AI & ML interests
Multimodal Dialogue, Large Multimodal Model, Large Language Model
Recent Activity
updated
a dataset
about 22 hours ago
friedrichor/TUNA-Bench
updated
a model
3 days ago
friedrichor/Unite-Instruct-Qwen2-VL-7B
updated
a model
3 days ago
friedrichor/Unite-Instruct-Qwen2-VL-2B
Organizations
Collections
1
Papers
2
models
5

friedrichor/Unite-Instruct-Qwen2-VL-7B
Feature Extraction
•
Updated
•
3

friedrichor/Unite-Instruct-Qwen2-VL-2B
Feature Extraction
•
Updated
•
6

friedrichor/Unite-Base-Qwen2-VL-7B
Feature Extraction
•
Updated
•
6

friedrichor/Unite-Base-Qwen2-VL-2B
Feature Extraction
•
Updated
•
10

friedrichor/stable-diffusion-2-1-realistic
Text-to-Image
•
Updated
•
57
•
4
datasets
9
friedrichor/TUNA-Bench
Viewer
•
Updated
•
3.43k
•
107
friedrichor/Unite-Instruct-Retrieval-Train
Viewer
•
Updated
•
1.27M
•
232
•
1
friedrichor/Unite-Base-Retrieval-Train
Viewer
•
Updated
•
6.38M
•
468
friedrichor/ActivityNet_Captions
Viewer
•
Updated
•
19.8k
•
159
•
1
friedrichor/MSVD
Viewer
•
Updated
•
1.97k
•
134
•
1
friedrichor/MSR-VTT
Viewer
•
Updated
•
17k
•
404
•
1
friedrichor/DiDeMo
Viewer
•
Updated
•
9.4k
•
1.15k
•
3
friedrichor/PhotoChat_image
Viewer
•
Updated
•
8.54k
•
99
•
2
friedrichor/PhotoChat_120_square_HQ
Viewer
•
Updated
•
120
•
32