EMOVA Hugging Face

Enterprise

community

https://emova-ollm.github.io/

emova-ollm

Activity Feed

AI & ML interests

Omni-modal Large Language Models, Multi-modal Large Language Models (MLLMs), Emotional spoken dialogue

Recent Activity

racheltechie authored a paper 17 days ago

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement

huangrh9 authored a paper 17 days ago

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement

huangrh9 authored a paper 17 days ago

Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?

View all activity

Emova-ollm's activity

racheltechie

authored a paper 17 days ago

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement

Paper • 2504.01934 • Published 18 days ago • 22

huangrh9

authored 8 papers 17 days ago

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement

Paper • 2504.01934 • Published 18 days ago • 22

Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?

Paper • 2503.06252 • Published Mar 8

Efficient Multi-modal Large Language Models via Visual Token Grouping

Paper • 2411.17773 • Published Nov 26, 2024

AtomThink: A Slow Thinking Framework for Multimodal Mathematical Reasoning

Paper • 2411.11930 • Published Nov 18, 2024

HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models

Paper • 2407.08706 • Published Jul 11, 2024

GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training

Paper • 2308.11331 • Published Aug 22, 2023

DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability

Paper • 2308.09306 • Published Aug 18, 2023 • 1

FILIP: Fine-grained Interactive Language-Image Pre-Training

Paper • 2111.07783 • Published Nov 9, 2021

KaiChen1998

posted an update about 1 month ago

Post

4831

📢 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: Emova-ollm/EMOVA-demo