---
license: apache-2.0
datasets:
- harryhsing/AVQA-R1-6K
language:
- en
base_model:
- Qwen/Qwen2.5-Omni-7B
---
This repository contains the EchoInk-R1-7B model as presented in [EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning](https://arxiv.org/abs/2505.04623).

For training and inference, please refer to the Code: https://github.com/HarryHsing/EchoInk