English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent work in computer vision and cognitive reasoning has given rise to anincreasing adoption of the Violation-of-Expectation (VoE) paradigm in syntheticdatasets. Inspired by infant psychology, researchers are now evaluating amodel's ability to label scenes as either expected or surprising with knowledgeof only expected scenes. However, existing VoE-based 3D datasets in physicalreasoning provide mainly vision data with little to no heuristics or inductivebiases. Cognitive models of physical reasoning reveal infants create high-levelabstract representations of objects and interactions. Capitalizing on thisknowledge, we established a benchmark to study physical reasoning by curating anovel large-scale synthetic 3D VoE dataset armed with ground-truth heuristiclabels of causally relevant features and rules. To validate our dataset in fiveevent categories of physical reasoning, we benchmarked and analyzed humanperformance. We also proposed the Object File Physical Reasoning Network(OFPR-Net) which exploits the dataset's novel heuristics to outperform ourbaseline and ablation models. The OFPR-Net is also flexible in learning analternate physical reality, showcasing its ability to learn universal causalrelationships in physical reasoning to create systems with betterinterpretability.

A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories