-
公开(公告)号：US11948665B2
公开(公告)日：2024-04-02
申请号：US17001068
申请日：2020-08-24
申请人： Salesforce, Inc.
发明人： Ali Madani , Bryan McCann , Nikhil Naik
IPC分类号： G16B40/30 , G06F30/20 , G06F111/08 , G16B5/20 , G16B15/20 , G16B25/10 , G16B30/00 , G16B40/20 , G16B50/10
CPC分类号： G16B40/30 , G06F30/20 , G16B5/20 , G16B15/20 , G16B25/10 , G16B30/00 , G16B40/20 , G16B50/10 , G06F2111/08
摘要： The present disclosure provides systems and methods for controllable protein generation. According to some embodiments, the systems and methods leverage neural network models and techniques that have been developed for other fields, in particular, natural language processing (NLP). In some embodiments, the systems and methods use or employ models implemented with transformer architectures developed for language modeling and apply the same to generative modeling for protein engineering.
-
公开(公告)号：US20240203532A1
公开(公告)日：2024-06-20
申请号：US18589215
申请日：2024-02-27
申请人： Salesforce, Inc.
发明人： Ali Madani , Bryan McCann , Nikhil Naik
IPC分类号： G16B40/30 , G06F30/20 , G06F111/08 , G16B5/20 , G16B15/20 , G16B25/10 , G16B30/00 , G16B40/20 , G16B50/10
CPC分类号： G16B40/30 , G06F30/20 , G16B5/20 , G16B15/20 , G16B25/10 , G16B30/00 , G16B40/20 , G16B50/10 , G06F2111/08
摘要： The present disclosure provides systems and methods for controllable protein generation. According to some embodiments, the systems and methods leverage neural network models and techniques that have been developed for other fields, in particular, natural language processing (NLP). In some embodiments, the systems and methods use or employ models implemented with transformer architectures developed for language modeling and apply the same to generative modeling for protein engineering.
-
公开(公告)号：US20240161248A1
公开(公告)日：2024-05-16
申请号：US18175156
申请日：2023-02-27
申请人： Salesforce Inc.
发明人： Nikhil Naik , Bram Wallace
CPC分类号： G06T5/002 , G06T5/30 , G06T5/50 , G06T2207/20081 , G06T2207/20084 , G06T2207/20216
摘要： Embodiments described herein provide systems and methods for image editing. a first copy and a second copy of an input image are generated; noise is iteratively added to the first copy and the second copy by: updating the first copy based on a first inverted output of a denoising diffusion model (DDM) based on the second copy and a first caption and updating the second copy based on a second inverted output of the DDM based on the first copy and the first caption. A resultant noised image is iteratively denoised by a reverse process using the DDM conditioned on a second caption, thereby producing a final image.
-
公开(公告)号：US11941086B2
公开(公告)日：2024-03-26
申请号：US17209011
申请日：2021-03-22
申请人： Salesforce, Inc.
IPC分类号： G06F18/21 , G06F17/16 , G06F18/214 , G06N3/045 , G06N3/084 , G06N3/10 , G06T7/194 , G06V10/25 , G06V10/46
CPC分类号： G06F18/2193 , G06F17/16 , G06F18/214 , G06N3/045 , G06N3/084 , G06N3/10 , G06T7/194 , G06V10/25 , G06V10/462 , G06T2207/20084
摘要： Embodiments described herein embodiments described herein provide Contrastive Attention-Supervised Tuning (CAST), a training method to fix the visual grounding ability of contrastive SSL methods based on a data augmentation strategy using unsupervised saliency maps. In addition to the contrastive loss that encourages the model to pick the crop that comes from the corresponding image, CAST provides an explicit grounding supervision through a Grad-CAM based attention loss that enforces models to look at the specified object of interest that is common across different crops when making this decision. A new geometric transform is introduced for randomly cropping different views from an input image based on certain constraints derived from a saliency map.
-
公开(公告)号：US20240303873A1
公开(公告)日：2024-09-12
申请号：US18333695
申请日：2023-06-13
申请人： Salesforce, Inc.
发明人： Bram Wallace , Nikhil Naik
CPC分类号： G06T11/00 , G06T5/70 , G06T2207/20084
摘要： Embodiments described herein provide a method of generating an image. the method comprises receiving, via a data interface, a natural language prompt, obtaining a noised image vector, and generating a denoised image vector by a first forward pass of a plurality of iterations of a denoising diffusion model with the noised image vector as an input and conditioned on the natural language prompt. The method further includes calculating a gradient of a loss function based on the denoised image vector with respect to the noised image vector, and updating the noised image vector based on the gradient. A final image is generated using a final forward pass of the denoising diffusion model with the updated noised image vector as an input and conditioned on the natural language prompt.
-
公开(公告)号：US11810298B2
公开(公告)日：2023-11-07
申请号：US17971312
申请日：2022-10-21
申请人： Salesforce, Inc.
发明人： Nikhil Naik , Ali Madani , Nitish Shirish Keskar
IPC分类号： G06T7/00 , G16H50/20 , G06N5/04 , G16H10/20 , G06N20/00 , G06F18/21 , G06F18/214 , G06V20/69
CPC分类号： G06T7/0012 , G06F18/217 , G06F18/2148 , G06N5/04 , G06N20/00 , G06V20/69 , G16H10/20 , G16H50/20 , G06V2201/03
摘要： An analytics system uses one or more machine-learned models to predict a hormone receptor status from a H&E stain image. The system partitions H&E stain images each into a plurality of non-overlapping image tiles. Bags of tiles are created through sampling of the image tiles. For each H&E stain image, the system generates a feature vector from a bag of tiles sampled from the partitioned image tiles. The analytics system trains one or more machine-learned models with training H&E stain images having a positive or negative receptor status. With the trained models, the analytics system predicts a hormone receptor status by applying a prediction model to the feature vector for a test H&E stain image.
-
公开(公告)号：US20230042318A1
公开(公告)日：2023-02-09
申请号：US17971312
申请日：2022-10-21
申请人： Salesforce, Inc.
发明人： Nikhil Naik , Ali Madani , Nitish Shirish Keskar
摘要： An analytics system uses one or more machine-learned models to predict a hormone receptor status from a H&E stain image. The system partitions H&E stain images each into a plurality of non-overlapping image tiles. Bags of tiles are created through sampling of the image tiles. For each H&E stain image, the system generates a feature vector from a bag of tiles sampled from the partitioned image tiles. The analytics system trains one or more machine-learned models with training H&E stain images having a positive or negative receptor status. With the trained models, the analytics system predicts a hormone receptor status by applying a prediction model to the feature vector for a test H&E stain image.
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.011 秒)
