Abstract: An approach to real-time multi-agent visual question answering in a decentralized environment. The approach can include initializing a plurality of agents based on data associated with an image and a question about the image. The approach can include identifying a first portion of the plurality of agents to construct a grid of agents based on similarity between the first portion of agents. The approach can include determining a second portion of agents of the first portion of agents with edges between agents allowing sharing of agent concepts and agent parameters. The approach can include generate training trajectories of the grid of agents based on executing a collaborative rollout. Additionally, the approach can include optimizing agent policies of the grid of agents.

Abstract: One embodiment provides a method, including: receiving, at an information handling device, drawing input; identifying, using a processor, at least one object in the drawing input; determining, based on the identifying, whether a factual anomaly exists in the drawing input with respect to the at least one object; and notifying, responsive to determining that a factual anomaly exists, a user of the factual anomaly.

Abstract: One embodiment provides a method, including: receiving, from a user, input for manipulating an image, wherein the input (i) identifies a particular image element and (ii) identifies an operation a user wants to perform with respect to the image element; identifying a context of the image, wherein the identifying the context comprises identifying (i) existing image elements already included within the image and (ii) attributes of the existing image elements; determining, based upon the context, attributes for the image element utilizing a knowledge store comprising information regarding attributes for image elements in view of (i) contexts and (ii) operations; and thereafter, performing the operation utilizing the image element having the attributes.

Abstract: One embodiment provides a method, including: receiving, from a user, input for manipulating an image, wherein the input (i) identifies a particular image element and (ii) identifies an operation a user wants to perform with respect to the image element; identifying a context of the image, wherein the identifying the context comprises identifying (i) existing image elements already included within the image and (ii) attributes of the existing image elements; determining, based upon the context, attributes for the image element utilizing a knowledge store comprising information regarding attributes for image elements in view of (i) contexts and (ii) operations; and thereafter, performing the operation utilizing the image element having the attributes.

Abstract: One embodiment provides a method, including: receiving, at an information handling device, drawing input; identifying, using a processor, at least one object in the drawing input; determining, based on the identifying, whether a factual anomaly exists in the drawing input with respect to the at least one object; and notifying, responsive to determining that a factual anomaly exists, a user of the factual anomaly.