Merced, CA, United States of America

Nakul Agarwal

This inventor holds 15 USPTO granted patents and 12 published patent applications, primarily in Video Understanding. Top assignees: Honda Motor Co., Ltd., Brown University, Leland Stanford Junior University. Active years: 2022-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Nakul Agarwal. Retrieved from https://idiyas.com/inventor/nakul-agarwal

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

Calculating rank
USPTO Granted Patents = 15 

% Patents Active = 100.0

Average Co-Inventor Count = 3.8

ph-index = 1

Forward Citations = 6(Granted Patents)


Location History:

  • Merced, CA (US) (2022)
  • San Jose, CA (US) (2023)
  • Santa Clara, CA (US) (2023)

Company Filing History:


Years Active: 2022-2026

Loading Chart...
Areas of Expertise:
Action Models
Neural Language Models
Spatial Action Localization
Motion Prediction
Vehicle Navigation
Passenger Intent Prediction
Weakly Supervised Segmentation
Plausible Action Anticipation
Driving Scenario Understanding
Driver Behavior Assessment
Pedestrian Awareness
Unsupervised Domain Adaptation
15 patents (USPTO):Explore Patents

Title: Nakul Agarwal: Innovator in Neural Networks and Action Anticipation

Introduction

Nakul Agarwal is a prominent inventor based in Merced, California. He has made significant contributions to the fields of neural networks and action anticipation, holding a total of 15 patents. His work focuses on enhancing the capabilities of artificial intelligence through innovative methodologies.

Latest Patents

One of Nakul's latest patents is titled "Systems and methods for training a neural network for generating a reasoning statement." This invention involves a method that receives sensor data from the perspective of an ego agent. It identifies captured objects in a roadway environment and generates a training dataset for object types, which includes natural language explanations for applied attributes. This method trains the neural network to produce reasoning statements based on detected objects.

Another notable patent is "Plausible action anticipation using large video-language models." This invention augments large video language models (LVLMs) by incorporating a plausible action anticipation framework. It focuses on the plausibility of action sequences and employs objective functions to train the LVLM, enabling it to generate temporally and spatially factual action sequences.

Career Highlights

Nakul Agarwal has worked with reputable organizations such as Honda Motor Co., Ltd. and Leland Stanford Junior University. His experience in these institutions has allowed him to refine his skills and contribute to groundbreaking research in artificial intelligence.

Collaborations

Throughout his career, Nakul has collaborated with talented individuals, including Behzad Dariush and Yi-Ting Chen. These collaborations have further enriched his work and expanded the impact of his inventions.

Conclusion

Nakul Agarwal is a distinguished inventor whose work in neural networks and action anticipation continues to push the boundaries of artificial intelligence. His innovative patents and collaborations reflect his commitment to advancing technology and enhancing machine learning capabilities.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…