arXiv:2606. 19635v1 Announce Type: cross Abstract: Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks.
arXiv:2607. 10016v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as backbone architectures for recommender systems because of their strong sequence modeling and representation learning capabilities.
arXiv:2608. 09605v1 Announce Type: cross Abstract: Large Language Models (LLMs) have emerged as powerful tools for improving recommendation 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.
Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length. In contrast, recommendation systems produce a single set of relevance scores for each pair without token-level supervision.
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:2607. 12281v1 Announce Type: cross Abstract: Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length.
arXiv:2607. 24845v1 Announce Type: cross Abstract: Large language models (LLMs) have been applied to sequential recommendation by formulating it as a natural language task.
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:2607. 24804v2 Announce Type: replace-cross Abstract: Recommendation systems have undergone significant transformations in the past years.
The paper introduces CRAFT, a Contextual Residual Adaptive Feature Transport block that treats unified recommendation models as a discrete context‑conditioned representation evolution process. By summarizing non‑sequential features into a reliability‑aware contextual field, CRAFT generates residual displacement and memory‑preserving signals to control intent and sequence representations. Experiments on the TAAC2026 competition show CRAFT achieving a test AUC of 0.838090, surpassing the previous best, and further improvements with deeper or wider models.
arXiv:2603.01590v2 Announce Type: replace-cross Abstract: Content-driven platforms such as Xiaohongshu often leverage click-through rate (CTR) prediction models for recommendation. However, these mod...
arXiv:2606. 00724v1 Announce Type: cross Abstract: Diffusion Large Language Models (DLMs) have demonstrated significant advantages across various tasks.