Patents by Inventor Jun Qian
Jun Qian has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 12371025Abstract: An autonomous lane change method includes: calculating a local neighbor feature and a global statistical feature of an autonomous vehicle at a current moment based on travel information of the autonomous vehicle at the current moment and motion information of obstacles in lanes within a sensing range of the autonomous vehicle; obtaining a target action indication based on the local neighbor feature, the global statistical feature, and a current control policy; and executing the target action according to the target action indication. On the basis of the local neighbor feature, the global statistical feature is further introduced into the current control policy to obtain the target action indication. The target action obtained by combining local and global road obstacle information is a globally optimal decision action.Type: GrantFiled: November 22, 2021Date of Patent: July 29, 2025Assignee: Huawei Technologies Co., Ltd.Inventors: Chen Chen, Jun Qian, Wulong Liu
-
Patent number: 12374139Abstract: Automated techniques are for generating a large volume of diverse training data that can be used for training machine learning models to extract KV pairs from document images. Given a single input document image and associated annotation data, a large number of diverse synthetic training datapoints are automatically generated by a synthetic data generation system, each datapoint including a synthetic document image and associated annotation data. The generated synthetic training datapoints can be used to train and improve the performance of ML models for extracting KV pairs from document images. In certain implementations, multiple synthetic datapoints are generated by varying the values associated with a key for a content item within the input document image.Type: GrantFiled: November 28, 2022Date of Patent: July 29, 2025Assignee: ORACLE INTERNATIONAL CORPORATIONInventors: Yazhe Hu, Tao Sheng, Jun Qian
-
Patent number: 12370646Abstract: Data received from an in-situ monitoring system includes, for each scan of a sensor, a plurality of measured signal values for a plurality of different locations on a layer. A thickness of a polishing pad is determined based on the data from the in-situ monitoring system. For each scan, a portion of the measured signal values are adjusted based on the thickness of the polishing pad. For each scan of the plurality of scans and each location of the plurality of different locations, a value is generated representing a thickness of the layer at the location. This includes processing the adjusted signal values using one or more processors configured by machine learning. A polishing endpoint is detected or a polishing parameter is modified based on the values representing the thicknesses at the plurality of different locations.Type: GrantFiled: November 23, 2022Date of Patent: July 29, 2025Assignee: Applied Materials, Inc.Inventors: Kun Xu, Denis Ivanov, Harry Q. Lee, Jun Qian
-
Patent number: 12361736Abstract: Techniques for multi-stage training of a machine learning model to extract key-value pairs from documents are disclosed. A system trains a machine learning model using a set of training data including unlabeled documents of various document categories. The initial stage identifies relationships among tokens, or words, numbers, and punctuation, in documents. The system re-trains the machine learning model using a set of training data which includes a particular category of documents while excluding other categories of documents. The second training stage is a supervised machine learning stage in which the training data is labeled to identify key-value pairs in the documents. In the initial training stage, the system sets parameters of the machine learning model to an initial state. In the second stage, the system modifies the parameters of the machine learning model based on the characteristics of the training data set including the documents of the particular category.Type: GrantFiled: January 4, 2023Date of Patent: July 15, 2025Inventors: Yazhe Hu, Jeaff Wang, Mengqing Guo, Tao Sheng, Jun Qian
-
Patent number: 12354871Abstract: Methods for depositing films by atomic layer deposition using aminosilanes are provided.Type: GrantFiled: March 22, 2023Date of Patent: July 8, 2025Assignee: Lam Research CorporationInventors: Jun Qian, Hu Kang, Adrien LaVoie, Seiji Matsuyama, Purushottam Kumar
-
Patent number: 12342844Abstract: The invention relates to a reconstituted plant leaf comprising plant fibres and a plant extract other than the tobacco plant suitable for devices that heat tobacco without burning it.Type: GrantFiled: August 30, 2018Date of Patent: July 1, 2025Assignee: SWM Holdings US, LLCInventors: Linda Lamblin, Stéphane Rouillard, Meng Jun Qian
-
Publication number: 20250201012Abstract: Techniques for constructing padding-sensitive batches for text recognition are provided. In one technique, a first bounding box from a list of bounding boxes is added or included into a batch of zero or more bounding boxes. Each bounding box in the list of bounding boxes surrounds different detected text in a digital image. A second bounding box is identified from the list. The second bounding box is wider than the first bounding box. A difference between (1) a width of the second bounding box and (2) a particular width is determined. The particular width is based on a width of a bounding box in the batch. Based on the difference and a threshold value, it is determined whether to include the second bounding box in the batch. The batch is then input into a test recognition model.Type: ApplicationFiled: December 19, 2023Publication date: June 19, 2025Inventors: Liyu Gong, Yuying Wang, Michael Avendi, Tao Sheng, Jun Qian
-
Publication number: 20250187135Abstract: During chemical mechanical polishing of a substrate, a signal value that depends on a thickness of a layer in a measurement spot on a substrate undergoing polishing is determined by a first in-situ monitoring system. An image of at least the measurement spot of the substrate is generated by a second in-situ imaging system. Machine vision processing, e.g., a convolutional neural network, is used to determine a characterizing value for the measurement spot based on the image. Then a measurement value is calculated based on both the characterizing value and the signal value.Type: ApplicationFiled: February 10, 2025Publication date: June 12, 2025Inventors: Benjamin Cherian, Jun Qian, Nicholas A. Wiswell, Dominic J. Benvegnu, Boguslaw A. Swedek, Thomas H. Osterheld
-
Publication number: 20250157210Abstract: Techniques are disclosed for dynamic time-based custom model generation as part of infrastructure-as-a-service (IaaS) environment. A custom model generation service may receive a set of training data and a time-based constraints for training a machine learning model. The custom model generation service may subsample the training data and generate a set of optimized tuned hyperparameters for a machine learning model to be trained using the subsampled training data. An experimental interval time of training is determined and the machine learning model is trained on the subsampled training data according to the optimized tuned hyperparameters over a set of training intervals similar to the experimental time interval. A customized machine learning model trained in the time-based constraint is output. The hyperparameter tuning may be performed using a modified mutating genetic algorithm for a set of hyperparameters to determine the optimized tuned hyperparameters prior to the training.Type: ApplicationFiled: January 15, 2025Publication date: May 15, 2025Applicant: Oracle International CorporationInventors: Olaitan Olaleye, Arunjeyan T V Seshier Venkatachalapathy, Jinghou Zhang, Jun Qian
-
Publication number: 20250124930Abstract: In an approach to improve the privacy of chat groups within a virtual world, embodiments of the present invention expand a chat area of a chat group to form an experience annulus according to predetermined distance that a voice volume of private-chat-group member can propagate. Responsive to identifying an external user is interested in the chat group, embodiments generate and set a current topic representing a conversation in the chat group as an externally hearable topic that is perceivable by the external user and generate a faux multi-person conversation associated with the externally hearable topic that corresponds to a real conversation made by members in the chat group. Further, embodiments assign the faux utterances to chat group members based on a corresponding speaker index and utilize one or more corresponding avatars of the chat group members to present the faux utterances to the external user.Type: ApplicationFiled: October 13, 2023Publication date: April 17, 2025Inventors: Jun Qian Zhou, Dan Zhang, Yuan Jie Song, Meng Chai, Xiao Feng Ji
-
Patent number: 12272047Abstract: A neural network is trained for use in a substrate residue classification system by obtaining ground truth residue level measurements of a top layer of a calibration substrate at a plurality of locations, each location at a defined position for a die being fabricated on the substrate. A plurality of color images of the calibration substrate are obtained, each color image corresponding to a region for a die being fabricated on the substrate. A neural network is trained to convert color images of die regions from an in-line substrate imager to residue level measurements for the top layer in the die region.Type: GrantFiled: October 27, 2023Date of Patent: April 8, 2025Assignee: Applied Materials, Inc.Inventors: Sivakumar Dhandapani, Arash Alahgholipouromrani, Dominic J. Benvegnu, Jun Qian, Kiran Lall Shrestha
-
Publication number: 20250107251Abstract: The present application discloses a method for making an image sensor, wherein an additional supplementary oxide layer is added in a PD area of a pixel cell before the formation of a gate oxide layer, a layer of a first photoresist is added and photoetching is used to define a PD area of a non-pixel cell, a supplementary oxide layer outside the PD area is removed by etching, retaining the supplementary oxide layer in the PD area. Thus, a relatively thick oxide layer can be formed in the PD area before polysilicon generation, blanket etching can be performed on the surface of the PD area during subsequent DG-ET (double-gate etching) and poly etch, and surface damage can be avoided during etching, reducing the plasma interference, and ultimately, the pixel dark current to improve pixel performance.Type: ApplicationFiled: May 14, 2024Publication date: March 27, 2025Applicant: Shanghai Huali Microelectronics CorporationInventors: Xing Fang, Chenchen Qiu, Jun Qian, Chang Sun, Zhengying Wei
-
Patent number: 12257665Abstract: During chemical mechanical polishing of a substrate, a signal value that depends on a thickness of a layer in a measurement spot on a substrate undergoing polishing is determined by a first in-situ monitoring system. An image of at least the measurement spot of the substrate is generated by a second in-situ imaging system. Machine vision processing, e.g., a convolutional neural network, is used to determine a characterizing value for the measurement spot based on the image. Then a measurement value is calculated based on both the characterizing value and the signal value.Type: GrantFiled: February 2, 2023Date of Patent: March 25, 2025Assignee: Applied Materials, Inc.Inventors: Benjamin Cherian, Jun Qian, Nicholas A. Wiswell, Dominic J. Benvegnu, Boguslaw A. Swedek, Thomas H. Osterheld
-
Patent number: 12261038Abstract: Provided herein are methods and apparatus for filling one or more gaps on a semiconductor substrate. The disclosed embodiments are especially useful for forming seam-free, void-free fill in both narrow and wide features. The methods may be performed without any intervening etching operations to achieve a single step deposition. In various implementations, a first operation is performed using a novel PEALD fill mechanism to fill narrow gaps and line wide gaps. A second operation may be performed using PECVD methods to continue filling the wide gaps.Type: GrantFiled: September 2, 2021Date of Patent: March 25, 2025Assignee: Lam Research CorporationInventors: Hu Kang, Shankar Swaminathan, Jun Qian, Wanki Kim, Dennis M. Hausmann, Bart J. van Schravendijk, Adrien LaVoie
-
Publication number: 20250094687Abstract: Techniques for generating repetition-free text using a large language model (LLM) are provided. In one technique, textual content that was generated by an LLM is accessed, where the textual content comprises a plurality of sub-components including a first sub-component and a second sub-component. A first embedding that represents the first sub-component is generated and a second embedding that represents the second sub-component is generated. Based on a similarity between the first embedding and the second embedding, it is determined whether the second sub-component is repetitious with respect to the first sub-component. In response to determining that the second sub-component is repetitious with respect to the first sub-component, at least a portion of the second sub-component is removed from the textual content.Type: ApplicationFiled: June 28, 2024Publication date: March 20, 2025Inventors: Zheng Wang, Yazhe Hu, Mengqing Guo, Tao Sheng, Jun Qian, Vinod Murli Mamtani
-
Publication number: 20250095096Abstract: The present disclosure relates to utilizing large language models (LLMs) to facilitate generation of incident reports or similar documents. One or more initial inputs may be received from a user, and one or more example incident reports may be identified. The one or more example incident reports and the one or more initial inputs may be sent to an LLM. A reviewable version of an incident report may be accessed that is based on output that the LLM generated based on the example incident reports and the one or more initial inputs. The reviewable version of the incident report may be presented in a human readable format via a graphical user interface (GUI). A modification corresponding to the reviewable version of the incident report may be received via the GUI. The modification and the reviewable version of the incident report may be sent to the LLM to cause the LLM to generate an updated version of the incident report.Type: ApplicationFiled: September 13, 2024Publication date: March 20, 2025Inventors: Iman Zadeh, Christophe J. Gerard, Qiu Qin, Ziqun Ye, Aditya Banerjee, Jun Qian, Nicole E. Hess
-
Publication number: 20250094816Abstract: Systems, methods, and other embodiments associated with automated fine-tuning of text generation for large language models are described herein. In one embodiment, a method accesses a collection of text samples. The text samples include a natural language text prompt that combines content and instructions. The method extracts the instructions from the text prompt. The method fine-tunes a large language model to generate text in natural language based on a text generation loss function that penalizes non-compliance with the extracted instructions by a generated text response to the text prompt. The method generates an evaluation score for performance of the tuned large language model as a text generator based on a value of the text generation loss function for a second generated text response. And, the method automatically signals that the fine tuning of the tuned large language model is complete in response to the evaluation score satisfying a threshold.Type: ApplicationFiled: April 30, 2024Publication date: March 20, 2025Inventors: Yazhe HU, Mengqing GUO, Zheng WANG, Tao SHENG, Jun QIAN, Vinod MAMTANI
-
Publication number: 20250094866Abstract: Techniques for correcting hallucinations produced by generative large language models (LLMs). In one technique, a computing system accesses first output generated by an LLM. The computing system identifies, within the first output, a plurality of assertions. The computing system determines that a first assertion in the plurality of assertions is false. The computing system generates a prompt that indicates that the first assertion is false. The computing system submits the prompt as input to the LLM. The computing system accesses second output that is generated by the LLM, where the second output includes a second assertion that is different than the first assertion and corresponds to the first assertion.Type: ApplicationFiled: May 30, 2024Publication date: March 20, 2025Inventors: Zheng Wang, Yazhe Hu, Mengqing Guo, Tao Sheng, Jun Qian, Vinod Murli Mamtani
-
Publication number: 20250094716Abstract: Techniques for language model (LM) summarization using semantical clustering are provided. In one technique, a plurality of concepts reflected in text data is identified. A plurality of concept clusters is generated based on similarity among the plurality of concepts. Thus, some concept clusters may include multiple concepts. For each concept cluster of the plurality of concept clusters, an LM generates a summary of the text corresponding to that concept cluster. A summary response of the text data is generated by aggregating the summary of each concept cluster of the plurality of concept clusters. In another technique, an LM generates a summary based on text data. A first set of concepts reflected in the summary is identified and a second set of concepts reflected in the text data is identified. A difference between the two sets may indicate that the summary is missing one or more concepts.Type: ApplicationFiled: May 7, 2024Publication date: March 20, 2025Inventors: Zheng Wang, Yazhe Hu, Mengqing Guo, Tao Sheng, Jun Qian, Vinod M. Mamtani
-
Publication number: 20250094865Abstract: Techniques for ensuring that language models follow instructions indicated in prompts are provided. In one technique, a first language model generates a response based on a prompt. A set of instructions in the prompt is identified. For each instruction in the set, a second language model determines whether the response indicates that the first language model followed the instruction. In another technique, for each prompt of a plurality of prompts: (1) a first language model generates a response based on the prompt; (2) multiple instructions are identified based on the prompt; (3) a second language model generates, based on the plurality of instructions, an output that indicates that the first language model followed each instruction; and (4) the prompt, the response, and the multiple instructions are stored in a training instance. The first language model is finetuned based on the training instances.Type: ApplicationFiled: April 8, 2024Publication date: March 20, 2025Inventors: Zheng Wang, Yazhe Hu, Mengqing Guo, Tao Sheng, Jun Qian, Vinod M. Mamtani