San Francisco, CA, United States of America

Ashish Teku Vaswani

This inventor holds 15 USPTO granted patents and 6 published patent applications, plus 3 CIPO patents and 2 EPO patents. Top assignee: Google Inc.. Active years: 2019-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Ashish Teku Vaswani. Retrieved from https://idiyas.com/inventor/ashish-teku-vaswani

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

USPTO Granted Patents = 15 (Patent Applications = 6)

% Patents Active = 93.3

CIPO Patents = 3

EPO Patents = 2 (Patent Applications = 11)

Average Co-Inventor Count = 6.5

ph-index = 4

Forward Citations = 92(Granted Patents)

Company Filing History:

15 out of 33,959

Google Inc.

patents

Years Active: 2019-2026

Loading Chart...

15 patents (USPTO):Sort by Forward CitationsExplore Patents

1. 12755520 - Local self-attention computer vision neural networks (2026-10-06),

2. 12354340 - Fully attentional computer vision (2025-07-08),

3. 12353991 - Fast decoding in sequence models using discrete latent variables (2025-07-08),

4. 12217173 - Attention-based sequence transduction neural networks (2025-02-04),

5. 12142034 - Attention-based image generation neural networks (2024-11-12),

6. 11893483 - Attention-based sequence transduction neural networks (2024-02-06),

7. 11816884 - Attention-based image generation neural networks (2023-11-14),

8. 11494561 - Multi-task multi-modal machine learning system (2022-11-08),

9. 11392790 - Attention-based image generation neural networks (2022-07-19),

10. 11113602 - Attention-based sequence transduction neural networks (2021-09-07),

11. 10956819 - Attention-based sequence transduction neural networks (2021-03-23),

12. 10839259 - Attention-based image generation neural networks (2020-11-17),

13. 10789427 - Multi-task multi-modal machine learning system (2020-09-29),

14. 10719764 - Attention-based sequence transduction neural networks (2020-07-21),

15. 10452978 - Attention-based sequence transduction neural networks (2019-10-22),

Title: Innovations of Ashish Teku Vaswani

Introduction

Ashish Teku Vaswani is a prominent inventor based in San Francisco, CA. He has made significant contributions to the field of computer vision and machine learning, holding a total of 14 patents. His work at Google Inc. has positioned him as a key figure in advancing technology.

Latest Patents

One of his latest patents is titled "Fully Attentional Computer Vision." This system is implemented as computer programs on one or more computers and includes a computer vision model with a positional local self-attention layer. This layer processes input feature maps to generate output feature maps by utilizing neighboring input elements and performing local self-attention operations. Another notable patent is "Fast Decoding in Sequence Models Using Discrete Latent Variables." This invention involves methods and systems for generating output sequences from input sequences using a latent prediction model and a parallel decoder model.

Career Highlights

Ashish has had a remarkable career at Google Inc., where he has been instrumental in developing innovative technologies. His expertise in computer vision and machine learning has led to advancements that are widely recognized in the tech industry.

Collaborations

He has collaborated with notable coworkers such as Niki J Parmar and Noam M Shazeer, contributing to various projects that enhance the capabilities of machine learning and artificial intelligence.

Conclusion

Ashish Teku Vaswani's contributions to technology through his patents and work at Google Inc. highlight his role as a leading inventor in the field. His innovative approaches continue to shape the future of computer vision and machine learning.

Profile summary based on public USPTO records.