Boe Technology Group Co., Ltd.

Tsinghua University

Microsoft Technology Licensing, LLC

Motorola Mobility LLC

Other

Intel Corporation

General Electric Company

Huawei Technologies Co., Limited

Chinese Academy of Sciences

Beijing Xiaomi Mobile Software Co., Ltd.

Asahi Glass Company, Limited

Alibaba Group Holding Limited

Hewlett-packard Development Company, L.p.

Rohm Co., Ltd.

Vmware, Inc.

Wei Zhang

Weiyun Huang

Zhanfeng Cao

Bin Zhang

Qi Liu

Qi Yao

Yu Zhang

Chao Li

Fang Liu

Jian Li

Dawei Shi

Ying Wang

Ming Hu

Benlian Wang

Liang Li

Chuncheng Che

Lei Zhang

Hui Li

Li Wang

Haifeng Wang

Greg S Melander

Zhen Zhang

Xin Zhou

Yuanhui Guo

Zhiwei Li

Yin Zhu

Taofeng Xie

Peng Xu

Jing Wang

Yuanjing Li

Xin Li

Hao Sun

Hao Chen

Feng Zhang

Yue Long

Ming Jin Chen

Jun Li

Chang Luo

Lili Du

Qiang Li

Errui Ding

Zhiqiang Wang

Yan Huang

Yi Wang

Xu Zhang

Yu Wang

Hao Liu

Yinong Liu

Xiaobo Wang

Feng Qu

Dong Li

Min He

Lei Guo

Xiaodong Xie

Yu Liu

Xiao Han

Jie Cui

Xin Zhao

Wei Lu

Yue Zhao

Yue Wang

Lei Wang

Wei Li

Wei Sun

Fan Yang

Bo Zhang

Yao Huang

Wei Chen

Liang Zhang

Bo Liu

Bo Yang

Ankur N Shah

Cheng Li

Yang Zhou

Zheng Wang

Tao Ma

Xing Zhang

Peng Li

Kun Tian

Bin Zhou

Tong Zhang

Qiang Fu

Yang Hu

Yanping Liao

Daniel R Tretter

Jian Nan Guo

Chuanxiang Xu

Xiaoou Tang

Qi Zhang

Tao Yang

Yong Wang

Ning Wang

Fengli Ji

Xi Li

Chen Zhao

Yan Zhang

Zhanchang Bu

Jie Liu

Xi Wang

Zhouchen Lin

Provided is a mask, including a mask frame and a mask body including a first mask region and a second mask region; the second mask region includes a first region and a second region; the first region is provided with a plurality of first through holes, and the second region is provided with a plurality of second through holes; the first through holes and the second through holes are arranged along a row direction and a column direction; a shape of the first through hole is a first shape, a shape of the second through hole is a second shape, and the second shape is a centrally symmetric pattern or an axially symmetric pattern; a ratio of a number of the second through holes to a number of the first through holes is less than or equal to 35%.

Mask and method for manufacturing same, display panel, and display device

A micro spectrum chip based on units of different shapes. The micro spectrum chip includes a CIS wafer and an optical modulation layer. The optical modulation layer includes several micro-nano structure units arranged on the surface of a photosensitive area of the CIS wafer. Each micro-nano structure unit includes a plurality of micro-nano structure arrays, and in each micro-nano structure unit, different micro-nano structure arrays are two-dimensional gratings composed of internal units of different shapes. In each micro-nano structure unit in this scheme, different micro-nano structure arrays have different shapes of internal units, and each group of micro-nano structure arrays have different modulation effects on lights with different wavelengths. The degree of freedom of 'shape' is fully utilized to obtain a rich modulation effect on the incident light. A two-dimensional grating structure based on internal units of different shapes is utilized.

Micro spectrum chip based on units of different shapes

Stylus

A biodegradable film is prepared from a composition that includes a copolyester obtained by extrusion reaction of a branched aliphatic-aromatic copolyester derived from monomer a, monomer b, monomer c and monomer d with an organic peroxide. The film can be completely degraded into small molecular products such as carbon dioxide, water and the like under natural or composting conditions. Moreover, the film can be prepared having a thickness of 4-50 μm as required, and its mechanical properties can reach the same level as or even better than those of LDPE film.

High strength ultra-thin biodegradable film and preparation method thereof

A projection apparatus including: a light source component; a light polarization component for converting light from the light source component into first polarized light in a first polarization direction; a display panel on a side, away from the light source component, of the light polarization component for adjusting the polarization direction of the first polarized light to emit second polarized light in a polarization direction between the first polarization direction and a second polarization direction, the first polarization direction is perpendicular to the second polarization direction; a light reflective component on a side, away from the light polarization component, of the display panel for reflecting one of the polarized light in the first polarization direction and the polarized light in the second polarization direction; a projection lens, a light incident surface of which faces the light reflective component so as to receive light reflected by the light reflective component.

Projection apparatus

A display panel having an active area includes: an array substrate and an opposite substrate disposed opposite to the array substrate. The array substrate includes a first substrate and a conductive structure disposed on the first substrate. The conductive structure is located on a side of the active area. On a side of the conductive structure away from the active area, a side surface of the conductive structure is substantially flush with a side surface of the first substrate. On the side where the conductive structure is located, an edge of an orthographic projection of the opposite substrate on a plane where the array substrate is located is located outside an edge of the array substrate.

Display panel including conductive structure and method for manufacturing the same, and display device

A display substrate includes an underlaying substrate, a display structure layer arranged on the underlaying substrate, and a light regulation layer arranged at a light exiting side of the display structure layer. The display structure layer includes multiple sub-pixels. An orthographic projection of the light regulation layer on the underlaying substrate does not overlap with opening regions of the multiple sub-pixels. The light regulation layer is configured to adjust an emergent direction of light of at least one color emitted from the display structure layer.

Display substrate and preparation method therefor, display device, and color filter substrate

An incremental learning method and apparatus for a large Vision-Language Model for autonomous driving are provided. The incremental learning method includes: expanding a first training sample set to obtain a second training sample set, wherein the second training sample set includes a plurality of image samples annotated with road scene targets; inserting a plurality of fine-tuning sub-networks respectively into specified positions in a first large Vision-Language Model to generate a second large Vision-Language Model; processing the image samples in the second training sample set using the second large Vision-Language Model to obtain a target prediction result; calculating a loss value using the target prediction result and a target annotation result; and preserving parameters of the first large Vision-Language Model unchanged, and updating parameters of the fine-tuning sub-networks using the loss value.

Incremental learning method and apparatus for large vision-language model for autonomous driving

Laser printer

A display substrate and a related device. The display substrate includes a plurality of first subpixels, a plurality of second subpixels and a plurality of third subpixels. In a first direction, the first subpixels and the third subpixels are arranged alternately to form a plurality of first subpixel rows, the second subpixels are arranged to form a plurality of second subpixel rows, and the first subpixel rows and the second subpixel rows are arranged alternately in a second direction. Lines connecting centers of two first subpixels and two third subpixels in two adjacent rows and columns form a first virtual quadrilateral, the two first/third subpixels are arranged at two/the other two opposite vertices of the first virtual quadrilateral respectively, and a corresponding second subpixel is located within the first virtual quadrilateral.

Display substrate and related device

A display substrate, including: a base substrate. The base substrate includes a display region, and the display region is provided with a plurality of sub-pixels and a conductive protective structure. At least one sub-pixel among the plurality of sub-pixels includes: a light-emitting element and a driving circuit that drives the light-emitting element to emit light. The light-emitting elements and the conductive protective structure are located on the side of the driving circuit away from the base substrate. The conductive protective structure includes at least one conductive part, and the at least one conductive part is located at an interval between respective light-emitting parts of light-emitting elements of at least two adjacent sub-pixels. The conductive protective structure is electrically connected to a signal terminal, and is configured to reduce carrier transmission between adjacent sub-pixels.

Display substrate, preparation method therefor, and display device for avoiding crosstalk defect

Cryo module

The present disclosure provides a liquid crystal grating and a driving method therefor, and a three-dimensional (3D) display device. The liquid crystal grating includes: a first substrate; a second substrate, where the second substrate and the first substrate are oppositely arranged; a liquid crystal layer, where the liquid crystal layer is located between the first substrate and the second substrate; and a first transparent grating electrode layer located at a side, facing the liquid crystal layer, of the first substrate; where the first transparent grating electrode layer includes a plurality of first strip-shaped electrodes extending in a first direction and arranged at intervals in a second direction, and each of at least part of the first strip-shaped electrodes is divided in the first direction into at least two first strip-shaped sub-electrodes arranged independently.

Liquid crystal grating and driving method therefor, and 3D display device

A method and an apparatus for collaborative end-to-end large model-oriented self-driving trajectory decision-making are provided. The method includes: processing an RGB image from ego vehicle, an RGB image from surrounding vehicle, and an RGB image from road-side by using a first feature extraction network to obtain a first image feature, a second image feature, and a third image feature, respectively; fusing first image feature, second image feature, and third image feature to obtain an image fusion feature; processing point cloud data of road-side to obtain a road-side point cloud feature; processing image fusion feature and road-side point cloud feature to obtain a first BEV feature and a second BEV feature; fusing first BEV feature and second BEV feature to obtain a fused BEV feature; and fusing prompt information and fused BEV feature to obtain text information, and then processing text information to obtain an ego vehicle trajectory decision-making result.

Method and apparatus for collaborative end-to-end large model-oriented self-driving trajectory decision-making

A multimodal perception decision-making method for autonomous driving based on a large language model includes: acquiring an RGB image and an infrared image of a target area at current time; processing the RGB image using a target detection model to obtain a predicted bounding box and a corresponding target detection category; processing the infrared image and the predicted bounding box and the corresponding target detection categories by using a segmentation model to obtain a target mask image; fusing the RGB image, the target mask image and the infrared image using a fusion model to obtain a fused feature map; performing fusion processing on first prompt information representing a user intent, second prompt information representing target detection category priorities, and the fused feature map, using a large Vision-Language Model to obtain textual information; and processing the textual information using a large natural language model to obtain a perception decision-making result.

Multimodal perception decision-making method and apparatus for autonomous driving based on large language model

Growing community of inventors

Beijing, China

Wei Zhang