arXiv AI
EASformer: Environment-Action-State Alignment for Industrial Generative Ranking
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 21
Dual-Interest Sequential Product Recommendation With Multi-Granular SSM
The paper introduces DSRec, a dual‑interest sequential recommendation model that separates item representations into long‑term and short‑term semantic contexts. Long‑term embeddings capture stable preferences through historical aggregation, while short‑term embeddings focus on local session intent modulated by inter‑click time intervals. Each branch is processed by a distinct State Space Model— a full‑sequence Mamba for long‑term modeling and a time‑modulated SSM for short‑term dynamics— and a residual cross‑fusion mechanism aligns the two granularities while preserving their independence. Experiments on public benchmarks show that DSRec outperforms state‑of‑the‑art methods.
arXiv AI
Jul 21
WHALE: A Scalable Unified Model for Recommendation with Wukong-HSTU Architecture
arXiv:2607. 17017v1 Announce Type: cross Abstract: As scalability becomes increasingly important in recommendation modeling, recent architectures have advanced the modeling of two broad sources of ranking signals along separate paths: non-sequence features, including user, item, context, and cross features; and sequence features from user behavior histories.
arXiv AI
Sep 2
From Language to Behavior: Scaling Sequence Transformers for Industrial Recommendation Ranking with Rec-Native Designs
The paper introduces ReST, a recommendation‑native Transformer scaling framework designed to handle noisy, irregular, and sparsely supervised user behavior sequences in production ranking. ReST employs a dual‑gated attention encoder with rotary positional and temporal embeddings, and a lightweight cross decoder that decouples heavy encoding from fast decoding, enabling efficient compute‑once, decode‑many‑times ranking. Experiments on industrial and public benchmarks show that ReST outperforms traditional Transformer blocks, achieving higher accuracy and consistent scaling across sequence length, depth, and width, and a one‑week online A/B test on a production advertising platform yielded a 1.31% AUC lift and an 11.93% increase in a core revenue metric within a 50 ms P99 latency budget.
arXiv AI
Aug 18
UniDot: A Unified Network for Sequence Modeling and Feature Interaction in Large-scale Recommendation
arXiv:2608. 16797v1 Announce Type: cross Abstract: Industrial recommenders rely on two model families that have evolved largely independently: feature-interaction models over multi-field user/item features, and sequential models over user-behavior histories.
arXiv AI
Sep 10
SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching
SequenceO1 is an end‑to‑end framework that enables ultra‑long (up to 100K interactions) sequence modeling for recommendation systems. It compresses raw user histories into a fixed‑size sketch using Sketch Attention and then models short‑term and long‑term interests with Target‑to‑History Cross Attention. The system incorporates low‑rank caching, batching, pipeline lift, and a FlashSA kernel to keep training and inference efficient, achieving consistent offline and online performance gains when deployed at full traffic on Douyin.
arXiv Machine Learning
Jun 25
TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems
arXiv:2606. 25147v1 Announce Type: cross Abstract: User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-dimensional vectors.