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/

Zendy Plus

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

Zendy Tools

Zendy Open

An interactive instruction following task has been proposed as a benchmarkfor learning to map natural language instructions and first-person vision intosequences of actions to interact with objects in 3D environments. We found thatan existing end-to-end neural model for this task tends to fail to interactwith objects of unseen attributes and follow various instructions. We assumethat this problem is caused by the high sensitivity of neural featureextraction to small changes in vision and language inputs. To mitigate thisproblem, we propose a neuro-symbolic approach that utilizes high-level symbolicfeatures, which are robust to small changes in raw inputs, as intermediaterepresentations. We verify the effectiveness of our model with the subtaskevaluation on the ALFRED benchmark. Our experiments show that our approachsignificantly outperforms the end-to-end neural model by 9, 46, and 74 pointsin the success rate on the ToggleObject, PickupObject, and SliceObject subtasksin unseen environments respectively.

Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following