Victor S. Bursztyn

Victor S. Bursztyn

PhD in Natural Language Processing (Northwestern University).

Research Scientist at Adobe Research.

Publicly Available Patents

Reducing hallucinations for generative text responses using a machine learning prompt ensemble.

U.S. Patent No. 18/612,566. Washington, DC: U.S. Patent and Trademark Office., 2025

Patent applied while at Adobe Research.

Recommended citation: Tong Yu, Xiang Chen, Victor S. Bursztyn, Sungchul Kim, Ryan A Rossi, Ruiyi Zhang, and Rui Wang. 2025. Reducing hallucinations for generative text responses using a machine learning prompt ensemble. U.S. Patent No. 18/612,566. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US11914635B2/en

Generating and executing action plans involving software tools via a large language model.

U.S. Patent No. 18/589,065. Washington, DC: U.S. Patent and Trademark Office., 2025

Patent applied while at Adobe Research.

Recommended citation: Yuchen Zhuang, Xiang Chen, Victor S. Bursztyn, Tong Yu, Somdeb Sarkhel, Saayan Mitra, and Ryan A Rossi. 2025. Generating and executing action plans involving software tools via a large language model. U.S. Patent No. 18/589,065. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US20250272544A1/en

In-context and semantic-aware ensemble model for document retrieval.

U.S. Patent No. 12,380,120. Washington, DC: U.S. Patent and Trademark Office., 2025

Patent applied while at Adobe Research.

Recommended citation: Tong Yu, Xiang Chen, Victor S. Bursztyn, Uttaran BHATTACHARYA, Eunyee Koh, Saayan Mitra, Alexandru Ionut Hodorogea, Kenneth Russell, Saurabh Tripathy, and Manas Garg. 2025. In-context and semantic-aware ensemble model for document retrieval. U.S. Patent No. 12,380,120. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US20250147973A1/en

Generating natural language model insights for data charts using light language models distilled from large language models.

U.S. Patent No. 18/338,033. Washington, DC: U.S. Patent and Trademark Office., 2024

Patent applied while at Adobe Research.

Recommended citation: Victor S. Bursztyn, Wei Zhang, Prithvi Bhutani, Eunyee Koh, and Abhisek Trivedi. 2024. Generating natural language model insights for data charts using light language models distilled from large language models. U.S. Patent No. 18/338,033. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US20240320421A1/en

Using generative artificial intelligence to evaluate fine-tuned language models.

U.S. Patent No. 18/485,204. Washington, DC: U.S. Patent and Trademark Office., 2024

Patent applied while at Adobe Research.

Recommended citation: Victor S. Bursztyn, Xiang Chen, Vaishnavi MUPPALA, Uttaran BHATTACHARYA, Tong Yu, Saayan Mitra, Ryan Rossi, Manas Garg, Kenneth George RUSSELL, Eunyee Koh, Alexandru Ionut Hodorogea. 2025. Using generative artificial intelligence to evaluate fine-tuned language models. U.S. Patent No. 18/485,204. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US20250124235A1/en

Method, Medium, and System for Recommending Compositions of Product Features Using Regression Trees.

U.S. Patent No. 11,030,667. Washington, DC: U.S. Patent and Trademark Office., 2021

Patent applied while at Dell EMC’s Brazil R&D Center.

Recommended citation: Adriana Bechara Prado, Victor S. Bursztyn, Jonas Furtado Dias, André de Almeida Maximo, and Angelo Ernani Maia Ciarlini. 2021. Method, Medium, and System for Recommending Compositions of Product Features Using Regression Trees. U.S. Patent No. 11,030,667. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US11030667B1/en

Relevance Decay for Time-based Evaluation of Machine Learning Applications.

U.S. Patent No. 10,885,464. Washington, DC: U.S. Patent and Trademark Office., 2021

Patent applied while at Dell EMC’s Brazil R&D Center.

Recommended citation: Diego Salomone Bruno, Victor S. Bursztyn, Percy Enrique Rivera Salas, and Tiago Salviano Calmon. 2021. Relevance Decay for Time-based Evaluation of Machine Learning Applications. U.S. Patent No. 10,885,464. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US10885464B1/en

Methods and Apparatus for a Semantic Multi-Database Data Lake.

U.S. Patent No. 10,901,973. Washington, DC: U.S. Patent and Trademark Office., 2021

Patent applied while at Dell EMC’s Brazil R&D Center.

Recommended citation: Rodrigo Dias Arruda Senra, Karin Breitman, Adriana Bechara Prado, and Victor S. Bursztyn. 2021. Methods and Apparatus for a Semantic Multi-Database Data Lake. U.S. Patent No. 10,901,973. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US10901973B1/en

Recommending Features for Content Planning Based on Advertiser Polling and Historical Audience Measurements.

U.S. Patent No. 10,448,120. Washington, DC: U.S. Patent and Trademark Office., 2019

Patent applied while at Dell EMC’s Brazil R&D Center.

Recommended citation: Victor S. Bursztyn, Jonas Furtado Dias, André de Almeida Maximo, Adriana Bechara Prado, and Rodrigo Dias Arruda Senra. 2019. Recommending Features for Content Planning Based on Advertiser Polling and Historical Audience Measurements. U.S. Patent No. 10,448,120. Washington, DC: U.S. Patent and Trademark Office. https://patents.google.com/patent/US10448120B1/en