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

We present GATSBI, a generative model that can transform a sequence of rawobservations into a structured latent representation that fully captures thespatio-temporal context of the agent's actions. In vision-based decision-makingscenarios, an agent faces complex high-dimensional observations where multipleentities interact with each other. The agent requires a good scenerepresentation of the visual observation that discerns essential components andconsistently propagates along the time horizon. Our method, GATSBI, utilizesunsupervised object-centric scene representation learning to separate an activeagent, static background, and passive objects. GATSBI then models theinteractions reflecting the causal relationships among decomposed entities andpredicts physically plausible future states. Our model generalizes to a varietyof environments where different types of robots and objects dynamicallyinteract with each other. We show GATSBI achieves superior performance on scenedecomposition and video prediction compared to its state-of-the-artcounterparts.

GATSBI: Generative Agent-centric Spatio-temporal Object Interaction