An end-to-end multimodal LLM for Scene Graph Generation (SGG), which was introduced in [Compile Scene Graphs with Reinforcement Learning](https://huggingface.co/papers/2504.13617

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for JosephZ/R1-SGG-Zero-7B

Base model

Qwen/Qwen2-VL-7B

Finetuned

Qwen/Qwen2-VL-7B-Instruct

Finetuned

(588)

this model

Dataset used to train JosephZ/R1-SGG-Zero-7B

Paper for JosephZ/R1-SGG-Zero-7B

Compile Scene Graphs with Reinforcement Learning

Paper • 2504.13617 • Published Apr 18, 2025