Abstract: Embodiments described herein provide a large language model (LLM) based AI agent that adopts Monte-Carlo Tree Search (MCTS) to execute a task. The LLM is prompted with a task description and it responds with its first attempted list of actions. Based on the success or failure of the first attempt, the LLM is prompted with an updated prompt which includes feedback from the first attempt based on a determined reward. The prompt may include a relative “score” for each action taken at each step. A numeric score may be mapped to a set of pre-defined text labels, such as “high” or “low” value putting the score in a form more suited for an LLM prompt. In this way, the LLM is iteratively given prompts which are updated with the scores from each action taken at each previous iterations so that it traverses different paths on the tree in each iteration.

Abstract: An electronic printing system includes an imaging apparatus and an electronic paper that can be detached from each other and can be coupled together to perform one or more functionalities. The imaging apparatus includes a first electrode and a first passivation layer. The electronic paper includes a second electrode, an electro-optic layer on the second electrode, and a second passivation layer on a side of the electro-optic layer away from the second electrode. When the imaging apparatus and the electronic paper are coupled together, the first electrode, the first passivation layer, the second passivation layer, the electro-optic layer, and the second electrode are sequentially arranged in a stacked structure, the first electrode and the second electrode being configured to apply an electric field to the electro-optic layer. The first passivation layer and the second passivation layer can be detached from each other.

Abstract: Methods, systems, apparatuses, devices, and computer program products are described. A flow generation service may receive a natural language input that indicates instructions for automating a task according to a first process flow. Using a large language model (LLM), the flow generation service may decompose the natural language input into a set of elements (e.g., logical actions) and connectors, where the LLM may be trained on first metadata corresponding to a second process flow that is created manually by a user. In addition, using the LLM, the flow generation service may generate second metadata corresponding to each of the set of elements based on decomposing the natural language input. The flow generation service may sequence and merge the set of elements to generate the first process flow. In some examples, the flow generation service may send, for display to a user interface of a user device, the first process flow.

Abstract: Embodiments described herein provide an online domain adaptation framework based on cross-domain bootstrapping for online domain adaptation, in which the target domain streaming data is deleted immediately after adapted. At each online query, the data diversity is increased across domains by bootstrapping the source domain to form diverse combinations with the current target query. To fully take advantage of the valuable discrepancies among the diverse combinations, a set of independent learners are trained to preserve the differences. The knowledge of the learners is then integrated by exchanging their predicted pseudo-labels on the current target query to co-supervise the learning on the target domain, but without sharing the weights to maintain the learners' divergence.

Abstract: Embodiments described herein provide a method of predicting an action by a plurality of language model augmented agents (LAAs). In at least one embodiment, a controller receives a task instruction to be performed using an environment. The controller receives an observation of a first state from the environment. The controller selects a LAA from the plurality of LAAs based on the task instruction and the observation. The controller obtains an output from the selected LAA generated using an input combining the task instruction, the observation, and an LAA-specific prompt template. The controller determines the action based on the output. The controller causes the action to be performed on the environment thereby causing the first state of the environment to change to a second state.

Abstract: Embodiments described herein provide for optimizing a language model (LM) agent. In at least one embodiment, and LM agent comprises an “actor” LM and a “retrospective LM which provides reflections on attempts by the actor LM. The reflections are used to update subsequent prompts to the actor LM. Optimizing the LM agent comprises fine-tuning parameters of the retrospective LM while keeping parameters of the actor LM frozen. A gradient may be determined by a change in reward from the environment based on actions taken by the actor LM with and without a reflection of the retrospective LM. Using this gradient, parameters of the retrospective LM may be updated via backpropagation.

Abstract: A field extraction system that does not require field-level annotations for training is provided. Specifically, the training process is bootstrapped by mining pseudo-labels from unlabeled forms using simple rules. Then, a transformer-based structure is used to model interactions between text tokens in the input form and predict a field tag for each token accordingly. The pseudo-labels are used to supervise the transformer training. As the pseudo-labels are noisy, a refinement module that contains a sequence of branches is used to refine the pseudo-labels. Each of the refinement branches conducts field tagging and generates refined labels. At each stage, a branch is optimized by the labels ensembled from all previous branches to reduce label noise.

Abstract: Embodiments described herein provide systems and methods for multimodal layout generations for digital publications. The system may receive as inputs, a background image, one or more foreground texts, and one or more foreground images. Feature representations of the background image may be generated. The foreground inputs may be input to a layout generator which has cross attention to the background image feature representations in order to generate a layout comprising of bounding box parameters for each input item. A composite layout may be generated based on the inputs and generated bounding boxes. The resulting composite layout may then be displayed on a user interface.

Abstract: Embodiments described herein provide systems and methods for federated learning. A central system may store a neural network model which has a body of a number of layers, and a classification layer comprising class prototypes which classifies the latent representations output by the body of the model. The central system may initialize the class prototypes so that they are uniformly distributed in the representation space. The model and class prototypes may be broadcast to a number of client systems, which update the body of the model locally while keeping the class prototypes fixed. The clients may return information to the central system including updated local model parameters, and a local representation of the classes based on the latent representation of items in the local training data. Based on the information from the clients, the neural network model may be updated. This process may be repeated iteratively.

Abstract: An online system extracts information from non-fixed form documents. The online system receives an image of a form document and obtains a set of phrases and locations of the set of phrases on the form image. For at least one field, the online system determines key scores for the set of phrases. The online system identifies a set of candidate values for the field from the set of identified phrases and identifies a set of neighbors for each candidate value from the set of identified phrases. The online system determines neighbor scores, where a neighbor score for a candidate value and a respective neighbor is determined based on the key score for the neighbor and a spatial relationship of the neighbor to the candidate value. The online system selects a candidate value and a respective neighbor based on the neighbor score as the value and key for the field.

Abstract: Embodiments described herein provide an online domain adaptation framework based on cross-domain bootstrapping for online domain adaptation, in which the target domain streaming data is deleted immediately after adapted. At each online query, the data diversity is increased across domains by bootstrapping the source domain to form diverse combinations with the current target query. To fully take advantage of the valuable discrepancies among the diverse combinations, a set of independent learners are trained to preserve the differences. The knowledge of the learners is then integrated by exchanging their predicted pseudo-labels on the current target query to co-supervise the learning on the target domain, but without sharing the weights to maintain the learners' divergence.

Abstract: Embodiments described a field extraction system that does not require field-level annotations for training. Specifically, the training process is bootstrapped by mining pseudo-labels from unlabeled forms using simple rules. Then, a transformer-based structure is used to model interactions between text tokens in the input form and predict a field tag for each token accordingly. The pseudo-labels are used to supervise the transformer training. As the pseudo-labels are noisy, a refinement module that contains a sequence of branches is used to refine the pseudo-labels. Each of the refinement branches conducts field tagging and generates refined labels. At each stage, a branch is optimized by the labels ensembled from all previous branches to reduce label noise.

Abstract: Embodiments described a field extraction system that does not require field-level annotations for training. Specifically, the training process is bootstrapped by mining pseudo-labels from unlabeled forms using simple rules. Then, a transformer-based structure is used to model interactions between text tokens in the input form and predict a field tag for each token accordingly. The pseudo-labels are used to supervise the transformer training. As the pseudo-labels are noisy, a refinement module that contains a sequence of branches is used to refine the pseudo-labels. Each of the refinement branches conducts field tagging and generates refined labels. At each stage, a branch is optimized by the labels ensembled from all previous branches to reduce label noise.

Abstract: An online system extracts information from non-fixed form documents. The online system receives an image of a form document and obtains a set of phrases and locations of the set of phrases on the form image. For at least one field, the online system determines key scores for the set of phrases. The online system identifies a set of candidate values for the field from the set of identified phrases and identifies a set of neighbors for each candidate value from the set of identified phrases. The online system determines neighbor scores, where a neighbor score for a candidate value and a respective neighbor is determined based on the key score for the neighbor and a spatial relationship of the neighbor to the candidate value. The online system selects a candidate value and a respective neighbor based on the neighbor score as the value and key for the field.

Abstract: Embodiments described herein provide unsupervised density-based clustering to infer table structure from document. Specifically, a number of words are identified from a block of text in an noneditable document, and the spatial coordinates of each word relative to the rectangular region are identified. Based on the word density of the rectangular region, the words are grouped into clusters using a heuristic radius search method. Words that are grouped into the same cluster are determined to be the element that belong to the same cell. In this way, the cells of the table structure can be identified. Once the cells are identified based on the word density of the block of text, the identified cells can be expanded horizontally or grouped vertically to identify rows or columns of the table structure.

Abstract: Embodiments described herein provide unsupervised density-based clustering to infer table structure from document. Specifically, a number of words are identified from a block of text in an noneditable document, and the spatial coordinates of each word relative to the rectangular region are identified. Based on the word density of the rectangular region, the words are grouped into clusters using a heuristic radius search method. Words that are grouped into the same cluster are determined to be the element that belong to the same cell. In this way, the cells of the table structure can be identified. Once the cells are identified based on the word density of the block of text, the identified cells can be expanded horizontally or grouped vertically to identify rows or columns of the table structure.

Abstract: The disclosure discloses an organic electroluminescent display panel, a driving method thereof and a display device, where the dimming mode is taken to drive and each frame of scanning time is divided into the display area scanning time and the front-back porch time. Where each line of pixel circuits located in the display area of the organic electroluminescent display panel are scanned during the display area scanning time; and the drive circuit is adjusted during the front-back porch time. Where the front-back porch time is less than the display area scanning time, and the front-back porch time is the common multiple of the respective clock signal cycles in the gate drive circuit of the organic electroluminescent display panel.

Abstract: An organic light-emitting pixel driving circuit, a driving method thereof, and an organic light-emitting display panel are provided. The organic light-emitting pixel driving circuit includes a light-emitting element, a driving transistor, a first and a second initialization modules, a threshold detection module, a data write-in module, and a storage module. The driving transistor is configured to drive the light-emitting element. The first initialization module is configured to transmit a signal carried by a reference voltage line to the driving transistor. The second initialization module is configured to transmit a signal carried by an initialization signal line to the light-emitting element. The threshold detection module is configured to detect a threshold voltage of the driving transistor. The data write-in module is configured to transmit a signal carried by a data line to the pixel driving circuit. The storage module is configured to store a signal written in by the data line.

Abstract: A display panel and a threshold detection method are provided. The display panel includes a plurality of data signal lines configured to transmit data signals, a plurality of scanning lines configured to transmit driving signals, a plurality of reference voltage signal lines configured to transmit reference voltage signals, and a plurality of pixels enclosed and defined by the mutually insulated data signal lines and scanning lines. A pixel driving circuit is disposed in each pixel, and each pixel driving circuit corresponds to one data signal line and one reference voltage signal line. The pixel driving circuits are arranged in a plurality of rows.

Abstract: Disclosed are a display panel and an electronic device. The display panel includes sub-pixels arranged in an array, wherein each pixel row of the sub-pixels comprises 3n sub-pixels, with every six adjacent sub-pixels of the pixel row forming a pixel group, n?2, and the six adjacent sub-pixels of the pixel group are arranged in sequential order in a first direction parallel to the row direction. The display panel further includes a controller, where in a first display mode the controller controls each of the sub-pixels to be charged to emit light; and in a second display mode the controller controls at most two sub-pixels of each of the pixel groups in at least one of the pixel rows to not emit light, and controls at most two sub-pixels of the pixel group which have same order in two adjacent frames of pictures to not emit light.