Abstract: Examples are provided relating to system evolving architectures for refining media content editing systems. One aspect includes a method of refining a media content editing architecture, the method comprising: editing a media content using a large language model and a back-end tool service comprising a prompt pool and a plurality of application programming interfaces corresponding to a plurality of editing tools; publishing the edited media content; storing contextual information relating to the editing of the media content; and refining the media content editing architecture using the stored contextual information.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for long video understanding. One of the methods includes obtaining a video; extracting frames from the video; encoding the extracted frames; extracting multimodal features including encoding speech content from the video as a text modality; encoding spatiotemporal dependencies between the extracted frames and aligned multi-modal features; providing the encoded temporal dependencies to a language model (LM) that learns spatiotemporal understanding of the entire video content; and using the language model to respond to user queries about the content of the video.

Abstract: Embodiments of the disclosure relate to a method, an apparatus, a device and a computer readable storage medium for generating data. The method proposed herein includes: obtaining a first feature representation by sampling from a target feature space, the target feature space being determined by processing a set of training samples with an encoding unit; processing the first feature representation with a diffusion unit to determine a second feature representation; and providing a second feature representation to a pre-trained language model to generate a target data sample.

Abstract: The present application discloses a model training method, an image editing method, an apparatus, a device, a medium, and a product. The method includes: first acquiring an original image, an editing description text corresponding to the original image, an edited image corresponding to the original image with respect to the editing description text, and evaluation information of the edited image, enabling the evaluation information to describe the state of the edited image in at least one evaluation item. Then the original image, the editing description text and the evaluation information by using an image editing model are processed to obtain an image editing result corresponding to the original image. According to the difference between the image editing result and the edited image, the image editing model is updated.

Abstract: The present disclosure describes techniques for improving efficiency and flexibility of a machine learning model. A machine learning model is configured to decompose self-attention in the machine learning model into a plurality of attention operations. The machine learning model is configured to process information from a plurality of modalities. Concatenated tokens are received by the machine learning model. The concatenated tokens comprise multimodal tokens representative of a content item and textual tokens indicative of a text query. Updated multimodal tokens for a next layer of computation are generated by performing diagonal-attention on the multimodal tokens. Updated textual tokens for the next layer of computation are generated by performing self-attention on the textual tokens and performing cross-attention between the multimodal tokens and the textual tokens.

Abstract: A method is provided for shunting route setting of a centralized traffic control system. The method includes S1, acquiring a shunting operation plan from an interface of a SMIS and generating a shunting route sequence, by a centralized traffic control system; S2, adding an operation direction, a location identifier of a shunter, a current control mode of the shunter and a description of a next route based on an original shunter number of the centralized traffic control system; S3, configuring a manual setting mode and an automatic triggering mode for shunting route setting; S4, adding identifiers of the manual setting mode and the automatic triggering mode to shunter number display; and S5, in the manual setting mode, adding a shunting plan constraint state and a free setting state to a shunting route setting logic of the centralized traffic control system.

Abstract: The present disclosure describes techniques for generating video descriptions using a machine learning model. A plurality of sets of visual tokens corresponding to a plurality of frames of a video is generated. A first type of tokens is generated by implementing temporal pooling on the plurality of sets of visual tokens corresponding to the plurality of frames. A second type of tokens is generated by compressing each of the plurality of sets of visual tokens corresponding to each of the plurality of frames. A third type of tokens is generated by applying cross-attention between each of the plurality of sets of visual tokens and a fourth type of tokens including text tokens generated based on an input text query. A text description of the video is generated based on the first type of tokens, the second type of tokens, the third type of tokens, and the fourth type of tokens.

Abstract: Embodiments of the disclosure relate to a method, an apparatus, a device, and a computer-readable storage medium for training a generative model. The method includes: constructing a training prompt; and performing a plurality of rounds of iterative training based on the training prompt, wherein each round of iterative training includes: obtaining a plurality of response contents generated by the generative model based on the training prompt; determining a first response content and a second response content from the plurality of response contents based on evaluation information of the plurality of response contents, wherein an evaluation of the first response content is superior to an evaluation of the second response content; and adjusting a parameter of the generative model to increase a first probability of outputting the first response content and reduce a second probability of outputting the second response content.

Abstract: A method, apparatus, device, and computer-readable storage medium for image processing are provided. The method includes receiving a text input for an initial image, the text input describing a visual effect for the initial image. A fusion feature for the text input and the initial image is generated based on the text input and the initial image. A target image corresponding to the initial image is generated based on a first image feature of the initial image and the fusion feature, the target image having a visual element related to the visual effect. The fusion of text and image can better express the desired visual effect.

Abstract: A display device and a driving method thereof are provided. The driving method includes the following steps: simultaneously controlling switches of an M-th row of sub-pixels and a (M+2)-th row of sub-pixels to be turned on or off, and sequentially controlling switches of four adjacent rows of the same color sub-pixels to be turned on or off.

Abstract: Examples are provided relating to system evolving architectures for refining media content editing systems. One aspect includes a method of refining a media content editing architecture, the method comprising: editing a media content using a large language model and a back-end tool service comprising a prompt pool and a plurality of application programming interfaces corresponding to a plurality of editing tools; publishing the edited media content; storing contextual information relating to the editing of the media content; and refining the media content editing architecture using the stored contextual information.

Abstract: A display panel and a display device are disclosed. The display panel includes a plurality of scan lines, a plurality of data lines, and a plurality of sub-pixels. Each of the scan lines is electrically connected to a row of the sub-pixels. The plurality of sub-pixels include a first pixel column and a second pixel column. The first pixel column and the second pixel column are arranged adjacent to each other. The first pixel column includes a plurality of first pixel units. The second pixel column includes a plurality of second pixel units. Each of the first pixel unit and the second pixel unit includes three sub-pixels, and colors of the three sub-pixels are different. At least two adjacent first pixel units and at least two adjacent second pixel units are electrically connected to a same data line.

Abstract: The present disclosure relates to systems and methods for image storage. The methods may include obtaining a first image of a subject. The methods may further include obtaining a second image of the subject. The second image may include scan status information of the subject. The scan status information may be associated with a status of the subject when the first image is acquired. And The methods may also include storing the second image correspondingly with the first image.

Abstract: Examples are provided relating to implementing actions on social media network content based on natural language inputs. One aspect includes a computing system configured to implement a social media network, comprising one or more processors, and a storage device comprising instructions executable to receive a user input including a natural language description of a request for an action on a content item from a dialogue agent configured to engage in dialogue using at least a language model, and generate a prompt for the language model based at least on the user input. The instructions are further executable to input the prompt to the language model to generate output describing operations for implementing the action, call a backend service of the social media network to execute commands to implement the operations, and output a result of executing the commands.

Abstract: The present discloses provides the use of tributyrin as an additive for embryonic development culture medium in vitro, in the present disclosure, the tributyrin is applied as an additive to the development culture medium of mouse embryos in vitro for the first time, the tributyrin can significantly increase the rate of blastocyst, and reduce the ROS content in the embryos, improve the mitochondrial membrane potential in the embryos, increase the ATP level and the expression of antioxidant genes in the embryos, improve the DNA methylation and histone modification level in the embryos, promote the embryos development in vitro; In addition, tributyrin, as natural antioxidant and apparent drug, which is safe, non-toxic and side effects; the tributyrin provides strong support for the efficient embryos development of human assisted reproductive technology, mammalian fertilization embryos, parthenogenetic embryos and somatic cell cloned embryos and other embryo engineering technologies in vitro.

Abstract: The present disclosure is related to systems and methods for subject positioning. The method includes generating a reference subject model of a subject to be scanned by a medical device based on feature information of the subject and a scan protocol of the subject. The method includes generating a target subject model by performing one or more rendering operations on the reference subject model based on at least one rendering parameter associated with an image capturing device. The method includes generating a positioning result by integrating the target subject model with image data related to a scan scene of the subject captured by the image capturing device. The method includes positioning the subject based on the positioning result.

Abstract: The present disclosure describes techniques for searching editing components based on text using a machine learning model. A plurality of visual embeddings indicative of a plurality of visual editing components is acquired by the machine learning model. The plurality of visual embeddings indicative of the plurality of visual editing components is projected into a common space by a first sub-model of the machine learning model. A text query input is received by a user. A text embedding indicative of the text query is generated. The text embedding is projected into the common space by a second sub-model of the machine learning model. At least one visual editing component among the plurality of visual editing components is determined based on the projected text embedding and the plurality of projected visual embeddings in the common space. Information indicative of the at least one visual editing component is displayed via a user interface.

Abstract: Examples are provided relating to media content editing architectures utilizing machine learning techniques. One aspect includes a method for media content editing, the method comprising: receiving a media content from a user; receiving an editing request for the media content from the user; and editing the media content based on the editing request to generate edited media content by: retrieving a prompt from a prompt pool, wherein the retrieved prompt is selected based on the editing request; parsing the retrieved prompt and the editing request using a large language model to generate one or more editing actions to be performed on the media content; and performing the one or more editing actions on the media content to generate the edited media content.

Abstract: A stability assessment method of roadway surrounding rock includes: obtaining actual stratum rock parameters; establishing a two-dimensional geological model through numerical simulation based on a drill core columnar diagram and the actual stratum rock parameters; changing influencing factors, and recording amounts and acceleration values of deformation of roadway sidewalls, and whether failure occurs to obtain dynamic response characteristics of roadway surrounding rock, combining the changed influencing factors and the dynamic response characteristics as labels to obtain a dataset, and obtaining multiple datasets including the dataset; dividing the multiple datasets into a training set and a validation set, inputting the training set into a PSO-BP neural network and a GA-SVM deep learning model to obtain a preliminary stability assessment model, and adjusting and validating the preliminary stability assessment model by the validation set to obtain an optimized stability assessment model; and using the opti

Abstract: The present disclosure describes techniques for generating image descriptions using a machine learning model. Mixture of Experts (MoE) blocks are incorporated into a plurality of sub-models of the machine learning model. The first sub-model of the machine learning model comprises at least one first MoE block including a first plurality of experts. A second sub-model of the machine learning model comprises at least one second MoE block including a second plurality of experts. Only a subset of the first plurality of experts is activated to generate visual tokens based on an input image. Only a subset of the second plurality of experts is activated to project the visual tokens into an input space of the third sub-model. A text description of the input image is output by the third sub-model of the machine learning model.