Detecting Violations of Physical Common Sense in Images: A Challenge Dataset and Effective Model
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 10945-10954
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62206318, 62306344)
- Guangdong Basic and Applied Basic Research Foundation (2024A1515010253)
- Guangzhou Intelligent Educational Technology Collaborative Innovation Center Construction Project (2023B04J0004)
- Research Project on Large Model-Based Higher Education Institution Development Data Governance Technology (2025B04J0037)
This publication has 10 references indexed in Scilit:
- Detecting and Reducing the Factual Hallucinations of Large Language Models with Metamorphic TestingProceedings of the ACM on Software Engineering, 2025
- An Empirical Study of Code Clones from Commercial AI Code GeneratorsProceedings of the ACM on Software Engineering, 2025
- LIVE-GS: LLM Powers Interactive VR by Enhancing Gaussian Splatting2025
- How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suitesScience China Information Sciences, 2024
- A Review of Differentiable SimulatorsIEEE Access, 2024
- PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics2024
- Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video2024
- Vision-Language Models for Vision Tasks: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Physics-informed neural networks (PINNs) for fluid mechanics: a reviewActa Mechanica Sinica, 2021
- From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptionsTransactions of the Association for Computational Linguistics, 2014