Article
3
Junlin Zhou
jlzhou
AI & ML interests
None yet
Recent Activity
upvoted
an
article
6 days ago
You could have designed state of the art positional encoding
liked
a model
8 days ago
mistralai/Mistral-Small-3.1-24B-Instruct-2503
reacted
to
KaiChen1998's
post
with 👍
8 days ago
📢 Our EMOVA paper has been accepted by CVPR 2025, and we are glad to release all resources, including code (training & inference), datasets (training & evaluation), and checkpoints (EMOVA-3B/7B/72B)!
🤗 EMOVA is a novel end-to-end omni-modal LLM that can see, hear and speak. Given omni-modal (i.e., textual, visual and speech) inputs, EMOVA can generate both textual and speech responses with vivid emotional controls by utilizing the speech decoder and a style controller.
✨ EMOVA Highlights
✅ State-of-the-art omni-modality: EMOVA achieves SoTA comparable results on both vision-language and speech benchmarks simultaneously.
✅ Device adaptation: our codebase supports training/inference on both NVIDIA GPUs (e.g., A800 & H20) and Ascend NPUs (e.g., 910B3)!
✅ Modular design: we integrate multiple implementations of vision encoder, vision projector, and language model, even including the most recent DeepSeekMoE-tiny!
🔥 You are all welcome to try and star!
- Project page: https://emova-ollm.github.io/
- Github: https://github.com/emova-ollm/EMOVA
- Demo: https://huggingface.co/spaces/Emova-ollm/EMOVA-demo
Organizations
Articles
2
Article
3
Distributed SFT with trl and DeepSpeed Part 1: Starting Locally
Papers
1
models
2
datasets
None public yet