I am passionate about discovering and exploring business market gaps, taking particular joy in integrating rigorous AI research. Here are some selected proposals at Adobe, a testament to my journey of invention and design - each design, prototype, and demo recording is crafted by me.
I am passionate about discovering and exploring business market gaps, taking particular joy in integrating rigorous AI research. Here are some selected proposals at Adobe, a testament to my journey of invention and design - each design, prototype, and demo recording is crafted by me.
Catchy Content
Catchy Content
Why is nobody clicking your website?
This proposal can help Marketers and Content Creators understand which type of content engages well with users (indicated by views, clicks, etc). It uses topic models to convert long-form articles into tags and provide a snapshot view of content tags to such engagement metrics.
This proposal can help Marketers and Content Creators understand which type of content engages well with users (indicated by views, clicks, etc). It uses topic models to convert long-form articles into tags and provide a snapshot view of content tags to such engagement metrics.
Outcomes:
Presented in Adobe Summit 2021 [Video Link]
Media Coverage in Forrestor, Fast Company, and Adobe Blogs [one, two]
Also adapted the method for Creatives - [Video Link]
Patent filed.
Topic Models Image Tagging Readability
Contextual Alchemy
Contextual Alchemy
Reading, Reimagined
This proposal proposes to keep articles evergreen such that they resonate and remain relevant to readers through personalized examples. Using LLMs, it changes an example according to user topic interest, geographic region, or even generation.
This proposal proposes to keep articles evergreen such that they resonate and remain relevant to readers through personalized examples. Using LLMs, it changes an example according to user topic interest, geographic region, or even generation.
Outcomes:
Accepted at NeurIPS Workshop, 2023 [Poster] [Paper] [Website]
Presented at Adobe GenAI Internal Hackathon [Video Link]
Patent filed.
Large Langauge Model Fact-Checking Information Extraction
WorkInFlow
WorkInFlow
More Creating... Less Catching Up...
This proposal enables creatives to assign ad-hoc tasks to others within their network, based on profiles, availability, task preferences, and past interactions. It streamlines the tracking and communication process, alleviating the burden from creatives.
This proposal enables creatives to assign ad-hoc tasks to others within their network, based on profiles, availability, task preferences, and past interactions. It streamlines the tracking and communication process, alleviating the burden from creatives.
Outcomes:
Presented in Adobe Hackathon [Video Link]
Topic Models Profile Matching Load-Balancing
Content Tensor
Content Tensor
What to write about?
This proposal aids marketers in navigating their extensive content repositories to swiftly pinpoint strategic 'gaps.' Using few-shot classification, it tags content with custom strategies and accelerates the decision-making process for creating engaging content.
This proposal aids marketers in navigating their extensive content repositories to swiftly pinpoint strategic 'gaps.' Using few-shot classification, it tags content with custom strategies and accelerates the decision-making process for creating engaging content.
Outcomes:
Accepted till Semi-Finals of Adobe Summit 2022 [Video Link]
Few-Shot Classification