✨CauSight: Learning to Supersense for Visual Causal Discovery

📝 Summary:
CauSight is a novel vision-language model for visual causal discovery, inferring cause-effect relations in images. It uses the VCG-32K dataset and Tree-of-Causal-Thought, significantly outperforming GPT-4.1 with a threefold performance boost.

🔹 Publication Date: Published on Dec 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.01827
• PDF: https://arxiv.org/pdf/2512.01827
• Github: https://github.com/OpenCausaLab/CauSight

🔹 Models citing this paper:
• https://huggingface.co/OpenCausaLab/CauSight

✨ Datasets citing this paper:
• https://huggingface.co/datasets/OpenCausaLab/VCG-32K

==================================

For more data science resources:
✓ https://t.me/DataScienceT

#VisualCausalDiscovery #VisionLanguageModels #AI #DeepLearning #CausalInference