This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Google Inc.. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Ayan Chakrabarti and Efficient Transformer Attention.
Introduction
Ayan Chakrabarti is an inventor based in New York, NY (US), whose patent work addresses computational efficiency in attention-based machine-learning models. His listed employer is Google Inc.
Latest Patents
Chakrabarti is associated with one patent, titled “Leveraging Redundancy in Attention with Reuse Transformers.” The invention describes systems and methods for improving the computational efficiency of Transformers and other attention-based neural networks by reusing attention scores across layers or heads. In particular, it proposes reusing scores computed in one layer in one or more subsequent layers, with the goal of reducing self-attention computation while maintaining comparable or better results. His listed total is 1 patent.
Career Highlights
The available information connects Chakrabarti’s work at Google Inc. with research into more efficient Transformer architectures. The patent focuses on reducing repeated computation in attention-based models.
Collaborations
The listed coworkers associated with Chakrabarti are Venkata S. Bhojanapalli and Andreas Veit. Their names provide context for the collaborative research environment surrounding this work.
Conclusion
Ayan Chakrabarti’s patent highlights an approach to making attention-based machine-learning models more computationally efficient through the reuse of attention scores.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
