Patents by Inventor Nikhil Naik

Nikhil Naik 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).

  • Publication number: 20250052244
    Abstract: A compressor may a first scroll, a second scroll, and a valve assembly. The second scroll may include a discharge passage. The valve assembly may include a valve housing fixed relative to the second scroll and a valve member movably received in the valve housing. The valve housing may include a plurality of angled apertures that are angled relative to a direction in which the valve member moves between the open and closed positions. The valve member is movable relative to the valve housing and valve retainer between an open position and a closed position. When the valve member is in the open position, fluid is allowed to flow through the discharge passage and the angled apertures in the valve housing. When the valve member is in the closed position, fluid flow through the discharge passage and the angled apertures is restricted.
    Type: Application
    Filed: June 25, 2024
    Publication date: February 13, 2025
    Applicant: Copeland LP
    Inventors: Yogesh S. MAHURE, Nikhil NAIK, Mohak BEHL
  • Publication number: 20240386685
    Abstract: Embodiments described herein provide a 3D generation system from a single RGB image of an object by inferring the hidden 3D structure of objects based on 2D priors learnt by a generative model. Specifically, the 3D generation system may reconstruct the 3D structure of an object from an input of a single RGB image and optionally an associated depth estimate. For example, a radiance field is formulated to depict the input image in one viewpoint of the target 3D object, based on which other viewpoints of the 3D object can be inferred. Based on the visible surface depicted by the input image, points between the reference camera and the surface are assigned with zero density, and points on the surface are assigned with high density and color equal to the corresponding pixel in the input image.
    Type: Application
    Filed: December 13, 2023
    Publication date: November 21, 2024
    Inventors: Senthil Purushwalkam Shiva Prakash, Nikhil Naik
  • Publication number: 20240386653
    Abstract: Embodiments described herein provide a 3D generation system from a single RGB image of an object by inferring the hidden 3D structure of objects based on 2D priors learnt by a generative model. Specifically, the 3D generation system may reconstruct the 3D structure of an object from an input of a single RGB image and optionally an associated depth estimate. For example, a radiance field is formulated to depict the input image in one viewpoint of the target 3D object, based on which other viewpoints of the 3D object can be inferred. Based on the visible surface depicted by the input image, points between the reference camera and the surface are assigned with zero density, and points on the surface are assigned with high density and color equal to the corresponding pixel in the input image.
    Type: Application
    Filed: December 13, 2023
    Publication date: November 21, 2024
    Inventors: Senthil Purushwalkam Shiva Prakash, Nikhil Naik
  • Patent number: 12106541
    Abstract: Embodiments described herein provide an intelligent method to select instances, by utilizing unsupervised tracking for videos. Using this freely available form of supervision, a temporal constraint is adopted for selecting instances that ensures that different instances contain the same object while sampling the temporal augmentation from the video. In addition, using the information on the spatial extent of the tracked object, spatial constraints are applied to ensure that sampled instances overlap meaningfully with the tracked object. Taken together, these spatiotemporal constraints result in better supervisory signal for contrastive learning from videos.
    Type: Grant
    Filed: January 31, 2022
    Date of Patent: October 1, 2024
    Assignee: Salesforce, Inc.
    Inventors: Brian Chen, Ramprasaath Ramasamy Selvaraju, Juan Carlos Niebles Duque, Nikhil Naik
  • Publication number: 20240303873
    Abstract: 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.
    Type: Application
    Filed: June 13, 2023
    Publication date: September 12, 2024
    Inventors: Bram Wallace, Nikhil Naik
  • Publication number: 20240203532
    Abstract: 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.
    Type: Application
    Filed: February 27, 2024
    Publication date: June 20, 2024
    Inventors: Ali Madani, Bryan McCann, Nikhil Naik
  • Publication number: 20240161248
    Abstract: 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.
    Type: Application
    Filed: February 27, 2023
    Publication date: May 16, 2024
    Inventors: Nikhil Naik, Bram Wallace
  • Patent number: 11948665
    Abstract: 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.
    Type: Grant
    Filed: August 24, 2020
    Date of Patent: April 2, 2024
    Assignee: Salesforce, Inc.
    Inventors: Ali Madani, Bryan McCann, Nikhil Naik
  • Patent number: 11941086
    Abstract: 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.
    Type: Grant
    Filed: March 22, 2021
    Date of Patent: March 26, 2024
    Assignee: Salesforce, Inc.
    Inventors: Ramprasaath Ramasamy Selvaraju, Nikhil Naik
  • Patent number: 11810298
    Abstract: 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.
    Type: Grant
    Filed: October 21, 2022
    Date of Patent: November 7, 2023
    Assignee: Salesforce, Inc.
    Inventors: Nikhil Naik, Ali Madani, Nitish Shirish Keskar
  • Publication number: 20230154139
    Abstract: Embodiments described herein provide an intelligent method to select instances, by utilizing unsupervised tracking for videos. Using this freely available form of supervision, a temporal constraint is adopted for selecting instances that ensures that different instances contain the same object while sampling the temporal augmentation from the video. In addition, using the information on the spatial extent of the tracked object, spatial constraints are applied to ensure that sampled instances overlap meaningfully with the tracked object. Taken together, these spatiotemporal constraints result in better supervisory signal for contrastive learning from videos.
    Type: Application
    Filed: January 31, 2022
    Publication date: May 18, 2023
    Inventors: Brian Chen, Ramprasaath Ramasamy Selvaraju, Juan Carlos Niebles Duque, Nikhil Naik
  • Publication number: 20230042318
    Abstract: 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.
    Type: Application
    Filed: October 21, 2022
    Publication date: February 9, 2023
    Inventors: Nikhil Naik, Ali Madani, Nitish Shirish Keskar
  • Patent number: 11508481
    Abstract: 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 image tiles. Bags of tiles are created through sampling of the 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. The analytics system generates, via a tile featurization model, a tile feature vector for each image tile a test bag for a test H&E stain image. The analytics system generates, via an attention model, an aggregate feature vector for the test bag by aggregating the tile feature vectors of the test bag, wherein an attention weight is determined for each tile feature vector. The analytics system predicts a hormone receptor status by applying a prediction model to the aggregate feature vector for the test bag.
    Type: Grant
    Filed: June 8, 2020
    Date of Patent: November 22, 2022
    Assignee: Salesforce, Inc.
    Inventors: Nikhil Naik, Ali Madani, Nitish Shirish Keskar
  • Publication number: 20220156527
    Abstract: 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.
    Type: Application
    Filed: March 22, 2021
    Publication date: May 19, 2022
    Inventors: Ramprasaath Ramasamy Selvaraju, Nikhil Naik
  • Publication number: 20220156592
    Abstract: 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.
    Type: Application
    Filed: March 22, 2021
    Publication date: May 19, 2022
    Inventors: Ramprasaath Ramasamy Selvaraju, Nikhil Naik
  • Publication number: 20210280311
    Abstract: 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 image tiles. Bags of tiles are created through sampling of the 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. The analytics system generates, via a tile featurization model, a tile feature vector for each image tile a test bag for a test H&E stain image. The analytics system generates, via an attention model, an aggregate feature vector for the test bag by aggregating the tile feature vectors of the test bag, wherein an attention weight is determined for each tile feature vector. The analytics system predicts a hormone receptor status by applying a prediction model to the aggregate feature vector for the test bag.
    Type: Application
    Filed: June 8, 2020
    Publication date: September 9, 2021
    Inventors: Nikhil Naik, Ali Madani, Nitish Shirish Keskar
  • Publication number: 20210249105
    Abstract: 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.
    Type: Application
    Filed: August 24, 2020
    Publication date: August 12, 2021
    Inventors: Ali Madani, Bryan McCann, Nikhil Naik
  • Publication number: 20210249100
    Abstract: 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.
    Type: Application
    Filed: August 24, 2020
    Publication date: August 12, 2021
    Inventors: Ali Madani, Bryan McCann, Nikhil Naik
  • Publication number: 20210249104
    Abstract: 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.
    Type: Application
    Filed: August 24, 2020
    Publication date: August 12, 2021
    Inventors: Ali Madani, Bryan McCann, Nikhil Naik
  • Patent number: 10110875
    Abstract: A three dimensional image capture system includes: an image capture device configured to generate video data; a lens, coupled to the image capture device, configured to focus a left image and a right image; a microprism array, coupled to the lens, configured to horizontally deflect the left image and the right image; and an image processing unit, coupled to the image capture device, configured to calculate a depthmap from the left image and the right image in the video data, rendered by the microprism array.
    Type: Grant
    Filed: September 13, 2013
    Date of Patent: October 23, 2018
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Pranav Mistry, Nikhil Naik