SOURCE-LINKED INTELLIGENCE

SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Modeling long-term user behavior is central to sequential recommendation and billion-scale industrial recommender systems, yet production ranking models operate under strict latency, memory, communication, and training-throughput constraints. At the 100K scale, the challenge extends beyond attention complexity: raw sequence features must be stored, transferred, and repeatedly processed during training and online serving. Existing approaches based on history truncation, multi-stage behavior retrieval, compressed lifelong histories, or train-short/infer-long extrapolation either weaken end-to-en

Read original source ↗ Open in workspace

recordType

paper

region

Global