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

In recent years, vision-language research has shifted to study tasks whichrequire more complex reasoning, such as interactive question answering, visualcommon sense reasoning, and question-answer plausibility prediction. However,the datasets used for these problems fail to capture the complexity of realinputs and multimodal environments, such as ambiguous natural language requestsand diverse digital domains. We introduce Mobile app Tasks with IterativeFeedback (MoTIF), a dataset with natural language commands for the greatestnumber of interactive environments to date. MoTIF is the first to containnatural language requests for interactive environments that are notsatisfiable, and we obtain follow-up questions on this subset to enableresearch on task uncertainty resolution. We perform initial feasibilityclassification experiments and only reach an F1 score of 37.3, verifying theneed for richer vision-language representations and improved architectures toreason about task feasibility.

Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments