Using Compressed Representations to Adapt Generative Models to New Context Data
Summary
USPTO published patent application US20260093991A1 for methods and systems using compressed representations to adapt generative models to new context data. The application was filed on October 2, 2025, by inventors Yoel Yehuda Zeldes, Amir Zait, Efrat Farkash, Ilia Labzovsky, and Danny Karmon. The invention involves processing compressed representations with a trained compression model to generate responses to queries through a generative neural network.
What changed
USPTO published patent application US20260093991A1, a 23-page patent application titled 'Using Compressed Representations to Adapt Generative Models to New Context Data.' The invention covers methods and systems for receiving a query, processing context content items through a trained compression model to generate fixed-size compressed representations, aggregating these representations, and using a generative neural network to generate responses. CPC classifications include G06N 3/082, G06N 3/0475, and G06N 3/0495, indicating AI neural network innovations.
This is a routine patent application publication with no compliance requirements or deadlines. Companies developing AI systems with context adaptation capabilities may wish to review this application during freedom-to-operate analysis or patent landscape reviews. The filing date was October 2, 2025, with Application No. 19348164.
Archived snapshot
Apr 2, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
USING COMPRESSED REPRESENTATIONS TO ADAPT GENERATIVE MODELS TO NEW CONTEXT DATA
Application US20260093991A1 Kind: A1 Apr 02, 2026
Inventors
Yoel Yehuda Zeldes, Amir Zait, Efrat Farkash, Ilia Labzovsky, Danny Karmon
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a task. In one aspect, a method comprises: receiving a query for a task to be performed; receiving a plurality of context content items for the task; for each content item of the plurality of content items, processing an input comprising a representation of the content item using a trained compression model to generate a compressed representation of the content item comprising one or more vectors of a fixed size; generating, using the compressed representations, an aggregated compressed representation comprising one or more vectors that represents the plurality of content items; and processing an input comprising (i) the query and (ii) the aggregated compressed representation using a generative neural network to generate a response to the query.
CPC Classifications
G06N 3/082 G06N 3/0475 G06N 3/0495
Filing Date
2025-10-02
Application No.
19348164
Related changes
Get daily alerts for USPTO Patent Applications - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The plain-English summary, classification, and "what to do next" steps are AI-generated from the original text. Cite the source document, not the AI analysis.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - AI & Computing (G06N) publishes new changes.