TokenFormer: Unify the Multi-Field and Sequential Recommendation Worlds

• URL: http://arxiv.org/abs/2604.13737v1
• Date: Wed, 15 Apr 2026 11:25:46 GMT
• Title: TokenFormer: Unify the Multi-Field and Sequential Recommendation Worlds
• Abstract summary: We propose TokenFormer, a unified recommendation architecture with the following innovations.<n>First, we introduce a Bottom-Full-Top-Sliding (BFTS) attention scheme, which applies full self-attention in the lower layers and shrinking-window sliding attention in the upper layers.<n>Second, we introduce a Non-linear Interaction Representation (NLIR) that applies one-sided non-linear multiplicative transformations to the hidden states.
• Score: 17.505701673051405
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recommender systems have historically developed along two largely independent paradigms: feature interaction models for modeling correlations among multi-field categorical features, and sequential models for capturing user behavior dynamics from historical interaction sequences. Although recent trends attempt to bridge these paradigms within shared backbones, we empirically reveal that naive unifying these two branches may lead to a failure mode of Sequential Collapse Propagation (SCP). That is, the interaction with those dimensionally ill non-sequence fields leads to the dimensional collapse of the sequence features. To overcome this challenge, we propose TokenFormer, a unified recommendation architecture with the following innovations. First, we introduce a Bottom-Full-Top-Sliding (BFTS) attention scheme, which applies full self-attention in the lower layers and shrinking-window sliding attention in the upper layers. Second, we introduce a Non-Linear Interaction Representation (NLIR) that applies one-sided non-linear multiplicative transformations to the hidden states. Extensive experiments on public benchmarks and Tencent's advertising platform demonstrate state-of-the-art performance, while detailed analysis confirm that TokenFormer significantly improves dimensional robustness and representation discriminability under unified modeling.

Related papers

• POINTS-Seeker: Towards Training a Multimodal Agentic Search Model from Scratch [84.73366911912512]
  We introduce Agentic Seeding, a dedicated phase designed to weave the precursors necessary for eliciting agentic behaviors.<n>We propose V-Fold, an adaptive history-aware compression scheme that preserves recent dialogue turns in high fidelity while folding historical context into the visual space via rendering.<n>We develop POINTS-Seeker-8B, a state-of-the-art multimodal agentic search model that consistently outperforms existing models across six diverse benchmarks.
  arXiv  Detail & Related papers  (2026-04-15T16:09:37Z)
• UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? [50.92401586025528]
  Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear.<n>We introduce UniG2U-Bench, a comprehensive benchmark categorizing generation-to-understanding (G2U) evaluation into 7 regimes and 30 subtasks.
  arXiv  Detail & Related papers  (2026-03-03T18:36:16Z)
• MixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders [11.566232697512879]
  MixFormer is a unified Transformer-style architecture tailored for recommender systems.<n>It jointly models sequential behaviors and feature interactions within a single backbone.<n>Experiments on large-scale industrial datasets demonstrate that MixFormer consistently exhibits superior accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-02-15T11:53:30Z)
• HyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Prediction [8.97787361529607]
  This paper presents HyFormer, a unified hybrid transformer architecture that tightly integrates long-sequence modeling and feature interaction into a single backbone.<n>Experiments on billion-scale industrial datasets demonstrate that HyFormer consistently outperforms strong LONGER and RankMixer baselines.
  arXiv  Detail & Related papers  (2026-01-19T02:55:05Z)
• BLADE: A Behavior-Level Data Augmentation Framework with Dual Fusion Modeling for Multi-Behavior Sequential Recommendation [15.457239237638985]
  BLADE is a framework that enhances multi-behavior modeling while mitigating data sparsity.<n>We introduce a dual item-behavior fusion architecture that incorporates behavior information at both the input and intermediate levels.<n>Three behavior-level data augmentation methods operate directly on behavior sequences rather than core item sequences.
  arXiv  Detail & Related papers  (2025-12-15T04:02:53Z)
• Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines [8.895768051554162]
  We propose a novel generative pre-training paradigm for e-commerce recommender systems.<n>Our model learns to predict the Next Interest Flow, a dense vector sequence representing a user's future intent.<n>We present the All-domain Moveline Evolution Network (AMEN), a unified framework implementing our entire pipeline.
  arXiv  Detail & Related papers  (2025-10-13T12:13:17Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• LARES: Latent Reasoning for Sequential Recommendation [96.26996622771593]
  We present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation.<n>Our proposed approach employs a recurrent architecture that allows flexible expansion of reasoning depth without increasing parameter complexity.<n>Our framework exhibits seamless compatibility with existing advanced models, further improving their recommendation performance.
  arXiv  Detail & Related papers  (2025-05-22T16:22:54Z)
• BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendation [15.818669767036592]
  We propose a Behavior-Bind multi-modal Quantization for Sequential Recommendation (BBQRec) featuring dual-aligned quantization and semantics-aware sequence modeling.<n>BBQRec disentangles modality-agnostic behavioral patterns from noisy modality-specific features through contrastive codebook learning.<n>We design a discretized similarity reweighting mechanism that dynamically adjusts self-attention scores using quantized semantic relationships.
  arXiv  Detail & Related papers  (2025-04-09T07:19:48Z)
• Long-Sequence Recommendation Models Need Decoupled Embeddings [49.410906935283585]
  We identify and characterize a neglected deficiency in existing long-sequence recommendation models.<n>A single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes.<n>We propose the Decoupled Attention and Representation Embeddings (DARE) model, where two distinct embedding tables are learned separately to fully decouple attention and representation.
  arXiv  Detail & Related papers  (2024-10-03T15:45:15Z)
• On the Embedding Collapse when Scaling up Recommendation Models [53.66285358088788]
  We identify the embedding collapse phenomenon as the inhibition of scalability, wherein the embedding matrix tends to occupy a low-dimensional subspace. We propose a simple yet effective multi-embedding design incorporating embedding-set-specific interaction modules to learn embedding sets with large diversity.
  arXiv  Detail & Related papers  (2023-10-06T17:50:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.