MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Contextual Reasoning

Eileen Wang, Hiba Arnaout, Dhita Pratama, Shuo Yang, Dangyang Liu +4 more
3/1/2026
cs.AI

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

We present MMCOMET, the first multimodal commonsense knowledge graph (MMKG) that integrates physical, social, and eventive knowledge. MMCOMET extends the ATOMIC2020 knowledge graph to include a visual dimension, through an efficient image retrieval process, resulting in over 900K multimodal triples. This new resource addresses a major limitation of existing MMKGs in supporting complex reasoning tasks like image captioning and storytelling. Through a standard visual storytelling experiment, we show that our holistic approach enables the generation of richer, coherent, and contextually grounded stories than those produced using text-only knowledge. This resource establishes a new foundation for multimodal commonsense reasoning and narrative generation.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

VAT-KG: Knowledge-Intensive Multimodal Knowledge Graph Dataset for Retrieval-Augmented Generation

82% match2025

Multimodal Reasoning with Multimodal Knowledge Graph

82% match1 repo202024

MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods

81% match2026

Multimodal Commonsense Knowledge Distillation for Visual Question Answering

81% match2024

Fusing Pre-Trained Language Models with Multimodal Prompts through Reinforcement Learning

81% match2026

EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning

81% match2024

Cite this paper

@article{wang2026mmcomet,
  title  = {MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Contextual Reasoning},
  author = {Eileen Wang and Hiba Arnaout and Dhita Pratama and Shuo Yang and Dangyang Liu and Jie Yang and Josiah Poon and Jeff Pan and Caren Han},
  year   = {2026},
  eprint = {2603.01055},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.01055v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.01055.svg)](https://codeofpaper.com/paper/2603.01055)

Discussion