Efficient Decoding of Output Sequences Using Parameter Sharing
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, 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.
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
Named provisions
Related changes
Get daily alerts for ChangeBridge: Patent Apps - 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 ChangeBridge: Patent Apps - AI & Computing (G06N) publishes new changes.