In one embodiment, a method includes receiving a user request from a first user from a client system associated with a first user, wherein the user request comprise a gesture-input from the first user and a speech-input from the first user, determining an intent corresponding to the user request based on the gesture-input by a personalized gesture-classification model associated with the first user, executing one or more tasks based on the determined intent and the speech-input, and sending instructions for presenting execution results of the one or more tasks to the client system responsive the user request.

In one embodiment, a method includes detecting a user input comprising an incomplete gesture performed by one or more hands of a first user by a client system associated with the first user; selecting one or more candidate gestures from a plurality of pre-defined gestures by the client system based on a personalized gesture-recognition model, wherein each of the candidate gestures is associated with a confidence score representing a likelihood the first user intended to input the respective candidate gesture, and presenting one or more suggested inputs corresponding to one or more of the candidate gestures at the client system.

In one embodiment, a method includes initiating a communication session with a second client system associated with a second user via a communication network, wherein the communication session is initiated in a first modality, receiving a ping to the first client system from the communication network to evaluate available bandwidth on the communication network, estimating, by the first client system, an amount of bandwidth available on the communication network for use by the first client system, determining, by the first client system, the amount of bandwidth available on the communication network for use by the first client system is insufficient for the first modality, and switching the communication session with the second client system to a second modality by the first client system, wherein the second modality uses less bandwidth than the first modality.

In one embodiment, a method includes receiving a first user input by a first user at a client system associated with the first user, wherein the first user input is associated with a first language register, selecting a first language-register model from a plurality of language-register models based on the first language register by the client system, wherein the plurality of language-register models are each personalized with respect to the first user, and presenting a personalized first communication content generated based on the selected first language-register model at the client system.

In one embodiment, a method includes receiving a user input including a partial request from a client system of a first user, analyzing the user input to generate one or more candidate hypotheses based on a personalized language model where each of the candidate hypotheses includes one or more of an intent-suggestion or a slot-suggestion, sending instructions for presenting one or more suggested auto-completions corresponding to one or more of the candidate hypotheses, respectively, to the client system, where each suggested auto-completion comprises the partial request and the corresponding candidate hypothesis, receiving an indication of a selection by the first user of a first suggested auto-completion of the suggested auto-completions from the client system, and executing one or more tasks based on the first suggested auto-completion selected by the first user via one or more agents.

In one embodiment, a method includes receiving from a client system a user request from a first user, determining a necessity for resolving the first user to a known entity to execute one or more tasks associated with the user request based on privacy restrictions associated with the user request, determining a set of candidate entities for the first user based on one or more machine-learning models, each candidate entity being associated with a respective confidence score greater than a threshold score, sending instructions for prompting the first user to select a candidate entity from the set of candidate entities, resolving the first user to a selected candidate entity responsive to receiving a selection from the first user, and executing the one or more tasks associated with the user request based on a user profile associated with the selected candidate entity.

In one embodiment, a method includes receiving, from a client system via an assistant xbot of a messaging application, a first user input comprising a command for controlling a network-connected device, wherein the device is associated with a contact identifier (ID) in the messaging application, identifying the device based on the contact ID, generating one or more control instructions for the device based on the command, sending, to the device via a network, the control instructions to cause the device to perform one or more actions associated with the command, receiving, from the device via the network, a response to the command, and sending, to the client system via the assistant xbot, an output based on the response from the device. The first user input may include a character string that specifies the command or an indication of a selected user interface feature that corresponds to the command.

In one embodiment, a method includes receiving a user request from a client system associated with a first user, wherein the user request is associated with a semantic-intent, identifying one or more dialog-intents associated with the user request based on the semantic-intent and context information associated with the user request, wherein each dialog-intent is a sub-intent of the semantic-intent, determining one or more agents for executing one or more tasks associated with the one or more dialog-intents, and sending instructions for presenting information returned from the one or more agents responsive to executing the one or more tasks to the client system.

A method includes detecting a user input comprising an incomplete three-dimensional (3D) gesture performed by one or more hands of a first user by a virtual-reality (VR) headset, selecting candidate 3D gestures from pre-defined 3D gestures based on a personalized gesture-recognition model, wherein each of the candidate 3D gestures is associated with a confidence score representing a likelihood the first user intended to input the respective candidate 3D gesture, and presenting one or more suggested inputs corresponding to one or more of the candidate 3D gestures at the VR headset.

In one embodiment, a method includes, by one or more computing systems of a communication network, receiving, from a first client system associated with a first user during a communication session between the first client system and a second client system associated with a second user, a first user communication in a first modality, wherein the first user communication is to be sent via the network to the second client system. The method further includes determining an available bandwidth of the network with respect to the second client system, determining a second modality to send the first user communication to the second client system based on the available bandwidth, generating a second user communication in the second modality by converting the first user communication to the second modality, and sending, to the second client system the second user communication for presentation to the second user.