ch-min/Qwen2.5-VL-3B-Instruct-data_scale_exp_800k-20251114_120221

Qwen2.5-VL-3B — Data-Scale Fine-tune (800k)

Fine-tune of `Qwen/Qwen2.5-VL-3B-Instruct` on a 5-dataset spatial-reasoning mixture (SAT + RoboSpatial + SPAR-7M + RefSpatial + PRISM), with the training-sample budget set to 800k.

This checkpoint is one of the data-scale variants released alongside the paper "Why Far Looks Up: Probing Spatial Representation in Vision-Language Models" (see HF Collection).

• —📄 Paper: arXiv:2605.30161
• —🌐 Project page: https://cheolhong0916.github.io/whyfarlooksup.github.io/
• —💻 Probing / evaluation code: https://github.com/cheolhong0916/contrastive-probing
• —📊 Diagnostic benchmark: `cubec/spatialtunnel`

Loading

This checkpoint inherits the architecture of `Qwen/Qwen2.5-VL-3B-Instruct`. Load it with the same interface you would use for the base model.

from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor

Citation

If you use this checkpoint, please cite both our paper and the original Qwen2.5-VL-3B paper.

Our paper (this checkpoint family):

@article{min2026whyfarlooksup,
  title   = {Why Far Looks Up: Probing Spatial Representation in Vision-Language Models},
  author  = {Min, Cheolhong and Jung, Jaeyun and Lee, Daeun and Jeon, Hyeonseong and
             Su, Yu and Tremblay, Jonathan and Song, Chan Hee and Park, Jaesik},
  journal = {arXiv preprint arXiv:2605.30161},
  year    = {2026},
}

Original Qwen2.5-VL-3B ([Qwen2.5-VL Technical Report](https://arxiv.org/abs/2502.13923)):

@article{bai2025qwen25vl,
  title   = {Qwen2.5-VL Technical Report},
  author  = {Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Jialin and others},
  journal = {arXiv preprint arXiv:2502.13923},
  year    = {2025},
}