paper-with-me

Papers

IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments

2025-06-11 · Florian Bordes, Quentin Garrido, Justine T Kao, Adina Williams, Michael Rabbat, Emmanuel Dupoux

We present IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning models. Building on the original IntPhys benchmark, IntPhys 2 focuses on four core principles related to macroscopic objects: Permanence, Immutability, Spatio-Temporal Continuity, and Solidity. These conditions are inspired by research into intuitive physical understanding emerging during early childhood. IntPhys 2 offers a comprehensive suite of tests, based on the violation of expectation framework, that challenge models to differentiate between possible and impossible events within controlled and diverse virtual environments. Alongside the benchmark, we provide performance evaluations of several state-of-the-art models. Our findings indicate that while these models demonstrate basic visual understanding, they face significant challenges in grasping intuitive physics across the four principles in complex scenes, with most models performing at chance levels (50%), in stark contrast to human performance, which achieves near-perfect accuracy. This underscores the gap between current models and human-like intuitive physics understanding, highlighting the need for advancements in model architectures and training methodologies.

📄 PDF Abstract BibTeX arXiv:2506.09849

Code (1)

facebookresearch/intphys2 공식 구현 pytorch

Tasks

Benchmarking

Similar Papers 제목 키워드 기반

IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning

2018-03-20 · Ronan Riochet, Mario Ynocente Castro, Mathieu Bernard, Adam Lerer 외

In order to reach human performance on complexvisual tasks, artificial systems need to incorporate a sig-nificant amount of understanding of the world in termsof macroscopic objects, movements, forces, etc. Inspiredby wo…

Opinion: Learning Intuitive Physics May Require More than Visual Data

2025-12-06 · Ellen Su, Solim Legris, Todd M. Gureckis, Mengye Ren arxiv

Humans expertly navigate the world by building rich internal models founded on an intuitive understanding of physics. Meanwhile, despite training on vast quantities of internet video data, state-of-the-art deep learning …

Probing Physics Knowledge Using Tools from Developmental Psychology

2018-04-03 · Luis Piloto, Ari Weinstein, Dhruva TB, Arun Ahuja 외

In order to build agents with a rich understanding of their environment, one key objective is to endow them with a grasp of intuitive physics; an ability to reason about three-dimensional objects, their dynamic interacti…

Pixels to Principles: Probing Intuitive Physics Understanding in Multimodal Language Models

2025-07-22 · Mohamad Ballout, Serwan Jassim, Elia Bruni arxiv

This paper presents a systematic evaluation of state-of-the-art multimodal large language models (MLLMs) on intuitive physics tasks using the GRASP and IntPhys 2 datasets. We assess the open-source models InternVL 2.5, Q…

Occlusion resistant learning of intuitive physics from videos

2020-04-30 · Ronan Riochet, Josef Sivic, Ivan Laptev, Emmanuel Dupoux

To reach human performance on complex tasks, a key ability for artificial systems is to understand physical interactions between objects, and predict future outcomes of a situation. This ability, often referred to as int…

Object