PHYRE: A New Benchmark for Physical Reasoning

proceedings.neurips.ccsite

NeurIPS'19, 2019. [All Versions]. A benchmark for AI physical reasoning.

from

AGI & CoCoSci

added

2026-10-10

likes

0

similar

1. ▲
   Phy-Q as a measure for physical reasoning intelligence nature.com

   site category #agi-cocosci link ↗

   Nature Machine Intelligence, 2023. [NMI Challenge]. An interactive benchmark for AI physical reasoning.

   
2. ▲
   PIQA: Reasoning about Physical Commonsense in Natural Language arxiv.org

   site category #agi-cocosci link ↗

   AAAI'20, 2020. [All Versions].

3. ▲
   Partial Mental Simulation Explains Fallacies in Physical Reasoning psyarxiv.com

   site category #agi-cocosci link ↗

   Cognitive Neuropsychology, 2022. [All Versions].

4. ▲
   Fast and flexible: Human program induction in abstract reasoning tasks arxiv.org

   site category #agi-cocosci link ↗

   CogSci'21, 2021. [All Versions].

5. ▲
   Physion: Evaluating Physical Prediction from Vision in Humans and Machines openreview.net

   site category #agi-cocosci link ↗

   NeurIPS'21, 2021. [All Versions].

6. ▲
   AGENT: A Benchmark for Core Psychological Reasoning proceedings.mlr.press

   site category #agi-cocosci link ↗

   ICML'21, 2021. [All Versions]. Inspired by cognitive development studies on intuitive psychology, this paper presents a benchmark consisting of a large dataset of procedurally generated 3D animations, AGENT (Action, Goal, Efficiency, coNstraint, uTility), structured around four…

AGI & CoCoSci › Papers > Commonsense > Intuitive Physics: “NeurIPS'19, 2019. [All Versions]. A benchmark for AI physical reasoning.”