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

People always desire an embodied agent that can perform a task byunderstanding language instruction. Moreover, they also want to monitor andexpect agents to understand commands the way they expected. But, how to buildsuch an embodied agent is still unclear. Recently, people can explore thisproblem with the Vision-and-Language Interaction benchmark ALFRED, whichrequires an agent to perform complicated daily household tasks followingnatural language instructions in unseen scenes. In this paper, we propose LEBP-- Language Expectation and Binding Policy Module to tackle the ALFRED. TheLEBP contains a two-stream process: 1) It first conducts a language expectationmodule to generate an expectation describing how to perform tasks byunderstanding the language instruction. The expectation consists of a sequenceof sub-steps for the task (e.g., Pick an apple). The expectation allows peopleto access and check the understanding results of instructions before the agenttakes actual actions, in case the task might go wrong. 2) Then, it uses thebinding policy module to bind sub-steps in expectation to actual actions tospecific scenarios. Actual actions include navigation and object manipulation.Experimental results suggest our approach achieves comparable performance tocurrently published SOTA methods and can avoid large decay from seen scenariosto unseen scenarios.

LEBP -- Language Expectation & Binding Policy: A Two-Stream Framework for Embodied Vision-and-Language Interaction Task Learning Agents