Project AURIONAI Use-Cases Research & Innovation
Kuaishou
recommendation

OneRec (V1)

Kuaishou generative recommender deployed in the main scene, +1.6% watch time.

KuaishouKuaishouChina
Figure from the OneRec (V1) paper: (a) Our proposed unified architecture for end-to-end generation.
Levelmodel
Classrecommendation
Parametersnot in the notes
Contextnot in the notes
Released26 Feb 2025
Opennessunknown
Runs onhyperscale cluster
Statusactive

Lineage

successor
OneRec (V1) to OneRec-Think: successor, medium confidenceOneRec (V1) to OneRec-V2: successor, high confidenceOneRec (V1)OneRec (V1)Kuaishou, Feb 2025OneRec-V2OneRec-V2Kuaishou, Aug 2025OneRec-ThinkOneRec-ThinkKuaishou, Oct 2025
KuaishouOneRec-Think is a child (successor)medium confidencenotes
KuaishouOneRec-V2 is a child (successor)high confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.

R&D Topics

Generative recommendationexemplar

Identity

Developer
Kuaishou
Family
not in the notes
Released
26 Feb 2025 sourcesannouncement page
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
MoE End-to-end generative encoder-decoder with sparse MoE; session-wise generation; Iterative Preference Alignment with DPO and a reward model
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
action
Output
action
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
internal only
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
hyperscale cluster
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment arxiv.org https://arxiv.org/abs/2502.18965
  2. arxiv.org/pdf/2502.18965 https://arxiv.org/pdf/2502.18965

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "OneRec (V1)", https://aurion.semai.id/models/kuaishou-onerec/, records of October 2026.