11 44 13

Yuhao Dong

THUdyh

AI & ML interests

None yet

Recent Activity

posted an update 2 days ago

🔥🔥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 https://huggingface.co/collections/THUdyh/ola-67b8220eb93406ec87aeec37. Try to build your own powerful omni-modal model with our data and models!

updated a collection 2 days ago

Ola

updated a collection 2 days ago

Ola

View all activity

Organizations

THUdyh's activity

posted an update 2 days ago

Post

1770

🔥🔥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!

posted an update 3 months ago

Post

1103

🚀🚀🚀Introducing Insight-V! An early attempt towards o1-like multi-modal reasoning.
We offer a structured long-chain visual reasoning data generation pipeline and a multi-agent system to unleash the reasoning potential of MLLMs.
📜 Paper: https://arxiv.org/abs/2411.14432
🛠️ Github: https://github.com/dongyh20/Insight-V
💼 Model Weight: THUdyh/insight-v-673f5e1dd8ab5f2d8d332035

posted an update 4 months ago

Post

3367

🔥🔥🔥Introducing Oryx-1.5!
A series of unified MLLMs with much stronger performance on all the image, video, and 3D benchmarks 😍
🛠️Github: https://github.com/Oryx-mllm/Oryx
🚀Model: THUdyh/oryx-15-6718c60763845525c2bba71d
🎨Demo: THUdyh/Oryx
👋Try the top-tier MLLM yourself!

👀Stay tuned for more explorations on MLLMs!