This repository contains the merged Hugging Face checkpoint used by EAGLE-360 for 360-degree panoramic object localization. Given a panoramic image and a target-object query, the model predicts the object's azimuth and elevation in degrees through multi-turn global-to-local reasoning.
The checkpoint is based on Qwen3-VL and fine-tuned with panoramic multi-turn reasoning and GRPO. It is intended to be used with the EAGLE-360 evaluation code and the panoramic Rolling RoPE patches provided in the project repository.
Please install the dependencies and apply the vLLM/Transformers panoramic patches from the EAGLE-360 project repository before running evaluation.
1python eval.py \
2 --model ./checkpoints/hf_merged \
3 --test_file ./eagle360_test/test.json \
4 --pano_dir ./eagle360_test/images \
5 --n_samples 50
1@misc{xu2026eagle360embodiedactiveglobaltolocal,
2 title={EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\circ$},
3 author={Jingtao Xu and Zizhuo Lin and Jianwen Sun and Yi Yang and Yawei Luo},
4 year={2026},
5 eprint={2607.02479},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV},
8 url={https://arxiv.org/abs/2607.02479},
9}
