Yuhao Dong

THUdyh's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked 2 datasets 1 day ago

SynthLabsAI/Big-Math-RL-Verified

Viewer • Updated 2 days ago • 251k • 1.3k • 84

PrimeIntellect/SYNTHETIC-1-SFT-Data

Viewer • Updated 8 days ago • 894k • 1.45k • 21

New activity in THUdyh/Oryx-ViT 1 day ago

visual embedding and text embedding projection

2

#1 opened 2 days ago by

MonoLeon

New activity in THUdyh/Ola-Image 3 days ago

Add pipeline tag

#1 opened 6 days ago by

nielsr

New activity in THUdyh/Ola-Video 3 days ago

Add pipeline tag

#1 opened 6 days ago by

nielsr

New activity in THUdyh/Ola_speech_encoders 3 days ago

Add model card

#1 opened 6 days ago by

nielsr

New activity in THUdyh/Ola-Data 5 days ago

Add dataset card

#2 opened 6 days ago by

nielsr

posted an update 7 days ago

view post

Post

1956

🔥🔥Introducing Ola! State-of-the-art omni-modal understanding model with advanced progressive modality alignment strategy!
Ola ranks #1 on OpenCompass Leaderboard (<10B)
.
📜Paper: https://arxiv.org/abs/2502.04328
🛠️Code: https://github.com/Ola-Omni/Ola

🛠️We have fully released our video&audio training data, intermediate image&video model at THUdyh/ola-67b8220eb93406ec87aeec37. Try to build your own powerful omni-modal model with our data and models!

See translation

👀

3

3

+

Reply

updated a collection 8 days ago

Ola

Collection

Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment • 4 items • Updated 8 days ago • 2

upvoted a paper 8 days ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published 8 days ago • 118

updated 2 models 8 days ago

THUdyh/Ola-Image

Image-Text-to-Text • Updated 3 days ago • 4

THUdyh/Ola-Video

Video-Text-to-Text • Updated 3 days ago • 8

updated a Space 8 days ago

Running on Zero

2

2

Ola

📊

Generate text and speech from image or video inputs

published 2 models 8 days ago

THUdyh/Ola-Video

Video-Text-to-Text • Updated 3 days ago • 8

THUdyh/Ola-Image

Image-Text-to-Text • Updated 3 days ago • 4

liked a dataset 9 days ago

Congliu/Chinese-DeepSeek-R1-Distill-data-110k

Viewer • Updated 8 days ago • 110k • 4.77k • 405

published a Space 9 days ago

Running on Zero

2

2

Ola

📊

Generate text and speech from image or video inputs