Changeflow GovPing Telecom & Technology Efficient Decoding of Output Sequences Using Pa...
Routine Notice Added Draft

Efficient Decoding of Output Sequences Using Parameter Sharing

Favicon for changeflow.com ChangeBridge: Patent Apps - AI & Computing (G06N)
Published
Detected
Email

Summary

USPTO published patent application US20260093982A1 for methods and systems enabling efficient decoding of output sequences using parameter sharing in machine learning tasks. The application, filed by six inventors including Adam Joshua Fisch and Tal Schuster, covers techniques for generating output sequences by processing embeddings through layer blocks until termination criteria are met.

What changed

USPTO published patent application US20260093982A1 on April 2, 2026, covering methods and systems for efficient machine learning decoding. The invention involves generating output sequences by creating current input sequences from preceding tokens, generating embeddings for each input, and processing these embeddings through layer blocks until termination criteria are satisfied. The application claims priority to European Application 19347594.

This is a patent application publication, not a regulatory requirement. Technology companies and manufacturers developing ML systems may wish to review the claims for freedom-to-operate considerations or licensing opportunities. No compliance deadlines or penalties apply to this notice.

Archived snapshot

Apr 2, 2026

GovPing 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.

← USPTO Patent Applications

EFFICIENT DECODING OF OUTPUT SEQUENCES USING PARAMETER SHARING

Application US20260093982A1 Kind: A1 Apr 02, 2026

Inventors

Adam Joshua Fisch, Tal Schuster, Hrayr Harutyunyan, Ziwei Ji, Seungyeon Kim, Sangmin Bae

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing a machine learning task. One of the methods includes generating an output sequence by, at each of a plurality of output time steps: generating a current input sequence from at least the tokens at output time steps that precede the output time step in the output sequence; generating a respective embedding for each input in the current input sequence; and processing the respective embeddings for the inputs in the current input sequence through one or more layer blocks in the sequence of layer blocks until a termination criterion is satisfied.

CPC Classifications

G06N 3/08

Filing Date

2025-10-01

Application No.

19347594

View original document →

Named provisions

Abstract - Efficient Decoding Methods

Get daily alerts for ChangeBridge: Patent Apps - AI & Computing (G06N)

Daily digest delivered to your inbox.

Free. Unsubscribe anytime.

About this page

What is GovPing?

Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission

What's from the agency?

Source document text, dates, docket IDs, and authority are extracted directly from USPTO.

What's AI-generated?

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.

Last updated

Classification

Agency
USPTO
Published
April 2nd, 2026
Instrument
Notice
Legal weight
Non-binding
Stage
Draft
Change scope
Minor
Document ID
US20260093982A1

Who this affects

Applies to
Technology companies Manufacturers
Industry sector
3341 Computer & Electronics Manufacturing 5112 Software & Technology
Activity scope
Patent Filing Machine Learning Decoding
Geographic scope
United States US

Taxonomy

Primary area
Intellectual Property
Operational domain
Legal
Topics
Artificial Intelligence Software & Technology

Get alerts for this source

We'll email you when ChangeBridge: Patent Apps - AI & Computing (G06N) publishes new changes.

Optional. Personalizes your daily digest.

Free. Unsubscribe anytime.