Papers
arxiv:2512.01827

CauSight: Learning to Supersense for Visual Causal Discovery

Published on Dec 1
· Submitted by Tianyu Li on Dec 2
Authors:
,
,
,
,
,

Abstract

A novel vision-language model, CauSight, performs visual causal discovery by inferring cause-and-effect relationships in images, outperforming GPT-4.1 with a significant performance boost.

AI-generated summary

Causal thinking enables humans to understand not just what is seen, but why it happens. To replicate this capability in modern AI systems, we introduce the task of visual causal discovery. It requires models to infer cause-and-effect relations among visual entities across diverse scenarios instead of merely perceiving their presence. To this end, we first construct the Visual Causal Graph dataset (VCG-32K), a large-scale collection of over 32,000 images annotated with entity-level causal graphs, and further develop CauSight, a novel vision-language model to perform visual causal discovery through causally aware reasoning. Our training recipe integrates three components: (1) training data curation from VCG-32K, (2) Tree-of-Causal-Thought (ToCT) for synthesizing reasoning trajectories, and (3) reinforcement learning with a designed causal reward to refine the reasoning policy. Experiments show that CauSight outperforms GPT-4.1 on visual causal discovery, achieving over a threefold performance boost (21% absolute gain). Our code, model, and dataset are fully open-sourced at project page: https://github.com/OpenCausaLab/CauSight.

Community

Paper author Paper submitter

We are excited to share our recent work on VLM reasoning titled "CauSight: Learning to Supersense for Visual Causal Discovery".

Paper: https://arxiv.org/abs/2512.01827
Github: https://github.com/OpenCausaLab/CauSight
Model: https://huggingface.co/OpenCausaLab/CauSight
Dataset: https://huggingface.co/datasets/OpenCausaLab/VCG-32K

Sign up or log in to comment

Models citing this paper 1

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2512.01827 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.