Salesforce Com, Inc.

Salesforce, Inc.

International Business Machines Corporation

Hung Le

Chu Hong Hoi

Yue Wang

Ashit Kumar Jain

Akhilesh Deepak Gotmare

Matthew Cowger

Mohit Chawla

William Lam

Caiming Xiong

Edwin Boaz Soenaryo

Doyen Sahoo

Dongxu Li

Aditya S Cetlur

Junhao Zhang

Embodiments described herein provide a reinforcement learning based framework engaging pretrained language models (LMs) for program synthesis tasks. Specifically, the framework adopts a training strategy that optimizes pretrained LMs for program synthesis tasks in an actor-critic approach.

Systems and methods for program synthesis

Embodiments described herein provide a video generation framework built on a decoupled multimodal cross-attention module to simultaneously condition the generation on both an input image and a text input. The video generation may thus be conditioned on the visual appearance of a target object reflected in the input image. In this way, zero-shot video generation may be achieved with little fine-tuning efforts.

Systems and methods for controllable video generation

A method for dialog state tracking includes decoding, by a fertility decoder, encoded dialog information associated with a dialog to generate fertilities for generating dialog states of the dialog. Each dialog state includes one or more domains. Each domain includes one or more slots. Each slot includes one or more slot tokens. The method further includes generating an input sequence to a state decoder based on the fertilities. A total number of each slot token in the input sequence is based on a corresponding fertility. The method further includes encoding, by a state encoder, the input sequence to the state decoder, and decoding, by the state decoder, the encoded input sequence to generate a complete sequence of the dialog states.

System and method for automatic task-oriented dialog system

A system and method for generating a response in a video grounded dialogue are provided. A video-grounded dialogue neural network language model receives video input and text input. The text input includes a dialogue history between the model and a human user and a current utterance by the user. Encoded video input is generated using video encoding layers. Encoded text input is generated using text encoding layers. The encoded video input and the encoded text input are concatenated in to a single input sequence. A generative pre-trained transformer model generates the response to the current utterance from the singe input sequence.

Spatial-temporal reasoning through pretrained language models for video-grounded dialogues

Systems and methods are provided for performing a video-grounded dialogue task by a neural network model using bi-directional spatial-temporal reasoning. According to some embodiments, the systems and methods implement a dual network architecture or framework. This framework includes one network or reasoning module that learns dependencies between text and video in the direction of spatial&#x2192;temporal, and another network or reasoning module that learns in the direction of temporal&#x2192;spatial. The output of the multimodal reasoning modules may be combined to learn dependencies between language features in dialogues. The result joint representation is used as a contextual feature to the decoding components which allow the model to semantically generate meaningful responses to the users. In some embodiments, pointer networks are extended to the video-grounded dialogue task to allow the model to point to specific tokens from multiple source sequences to generate responses.

Bi-directional spatial-temporal reasoning for video-grounded dialogues

A method for identifying a shared credential within a networked computing environment. The method includes a computer processor accessing information corresponding to an aggregated plurality of authentication events within a networked computing environment. The method further includes identifying one or more credentials that are associated with the aggregated plurality of authentication events. The method further includes analyzing a frequency of usage of a first credential that is included in the identified one or more credentials. The method further includes determining that the first credential is shared, based at least in part, on the analysis of the frequency of usage of the first credential in authentication events by one or more hosts, and information related to authentication events corresponding to the one or more hosts that utilize the credential in authentication events. The method further includes generating a report that identifies that the first credential is shared.

Retrospective discovery of shared credentials

A system and method for testing in a database system. In one embodiment, a method includes receiving an indication of one or more changes to a software application, wherein each change corresponds to a different version of the software application. The method further includes generating one or more virtual machines for a version of the software application in response to the indication, wherein the one or more virtual machines test the version of the software application.

Growing community of inventors

Singapore, Singapore

Hung Le