Hi-SAM: A Hierarchical Structure-Aware Multi-modal Framework for Large-Scale Recommendation

• URL: http://arxiv.org/abs/2602.11799v1
• Date: Thu, 12 Feb 2026 10:26:15 GMT
• Title: Hi-SAM: A Hierarchical Structure-Aware Multi-modal Framework for Large-Scale Recommendation
• Authors: Pingjun Pan, Tingting Zhou, Peiyao Lu, Tingting Fei, Hongxiang Chen, Chuanjiang Luo,
• Abstract summary: Hi-SAM is a Hierarchical Structure-Aware Multi-modal framework with two designs.<n>It unifies modalities via geometry-aware alignment and quantizes them via a coarse-to-fine strategy.<n> Deployed on a large-scale social platform, Hi-SAM achieved a 6.55% gain in the core online metric.
• Score: 1.0839192829439435
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-modal recommendation has gained traction as items possess rich attributes like text and images. Semantic ID-based approaches effectively discretize this information into compact tokens. However, two challenges persist: (1) Suboptimal Tokenization: existing methods (e.g., RQ-VAE) lack disentanglement between shared cross-modal semantics and modality-specific details, causing redundancy or collapse; (2) Architecture-Data Mismatch: vanilla Transformers treat semantic IDs as flat streams, ignoring the hierarchy of user interactions, items, and tokens. Expanding items into multiple tokens amplifies length and noise, biasing attention toward local details over holistic semantics. We propose Hi-SAM, a Hierarchical Structure-Aware Multi-modal framework with two designs: (1) Disentangled Semantic Tokenizer (DST): unifies modalities via geometry-aware alignment and quantizes them via a coarse-to-fine strategy. Shared codebooks distill consensus while modality-specific ones recover nuances from residuals, enforced by mutual information minimization; (2) Hierarchical Memory-Anchor Transformer (HMAT): splits positional encoding into inter- and intra-item subspaces via Hierarchical RoPE to restore hierarchy. It inserts Anchor Tokens to condense items into compact memory, retaining details for the current item while accessing history only through compressed summaries. Experiments on real-world datasets show consistent improvements over SOTA baselines, especially in cold-start scenarios. Deployed on a large-scale social platform serving millions of users, Hi-SAM achieved a 6.55% gain in the core online metric.

Related papers

• MoDora: Tree-Based Semi-Structured Document Analysis System [62.01015188258797]
  Semi-structured documents integrate diverse interleaved data elements arranged in various and often irregular layouts.<n>MoDora is an LLM-powered system for semi-structured document analysis.<n> Experiments show MoDora outperforms baselines by 5.97%-61.07% in accuracy.
  arXiv  Detail & Related papers  (2026-02-26T14:48:49Z)
• The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation [51.62815306481903]
  We propose textbfname, a novel framework that harmonizes the SID and HID. Specifically, we devise a dual-branch modeling architecture that enables the model to capture both the multi-granular semantics within SID while preserving the unique collaborative identity of HID.<n>Experiments on three real-world datasets show that name balances recommendation quality for both head and tail items while surpassing the existing baselines.
  arXiv  Detail & Related papers  (2025-12-11T07:50:53Z)
• FITRep: Attention-Guided Item Representation via MLLMs [8.026404756145485]
  We propose FITRep, the first attention-guided, white-box item representation framework for fine-grained item deduplication.<n> Deployed on Meituan's advertising system, FITRep achieves +3.60% CTR and +4.25% CPM gains in online A/B tests, demonstrating both effectiveness and real-world impact.
  arXiv  Detail & Related papers  (2025-11-26T13:38:19Z)
• MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns [80.05126590825121]
  MonkeyOCR v1.5 is a unified vision-language framework that enhances both layout understanding and content recognition.<n>To address complex table structures, we propose a visual consistency-based reinforcement learning scheme.<n>Two specialized modules, Image-Decoupled Table Parsing and Type-Guided Table Merging, are introduced to enable reliable parsing of tables.
  arXiv  Detail & Related papers  (2025-11-13T15:12:17Z)
• MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation [16.81485354427923]
  We propose Multimodal Mixture-of-Quantization (MMQ), a two-stage framework that trains a novel multimodal tokenizer.<n> MMQ unifies multimodal synergy, specificity, and behavioral adaptation, providing a scalable and versatile solution for both generative retrieval and discriminative ranking tasks.
  arXiv  Detail & Related papers  (2025-08-21T06:15:49Z)
• Integrating Extra Modality Helps Segmentor Find Camouflaged Objects Well [23.460400679372714]
  MultiCOS is a novel framework that effectively leverages diverse data modalities to improve segmentation performance.<n>BFSer outperforms existing multimodal baselines with both real and pseudo-modal data.
  arXiv  Detail & Related papers  (2025-02-20T11:49:50Z)
• Spatial Semantic Recurrent Mining for Referring Image Segmentation [63.34997546393106]
  We propose Stextsuperscript2RM to achieve high-quality cross-modality fusion. It follows a working strategy of trilogy: distributing language feature, spatial semantic recurrent coparsing, and parsed-semantic balancing. Our proposed method performs favorably against other state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2024-05-15T00:17:48Z)
• Preserving Modality Structure Improves Multi-Modal Learning [64.10085674834252]
  Self-supervised learning on large-scale multi-modal datasets allows learning semantically meaningful embeddings without relying on human annotations. These methods often struggle to generalize well on out-of-domain data as they ignore the semantic structure present in modality-specific embeddings. We propose a novel Semantic-Structure-Preserving Consistency approach to improve generalizability by preserving the modality-specific relationships in the joint embedding space.
  arXiv  Detail & Related papers  (2023-08-24T20:46:48Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• SWAT: Spatial Structure Within and Among Tokens [53.525469741515884]
  We argue that models can have significant gains when spatial structure is preserved during tokenization. We propose two key contributions: (1) Structure-aware Tokenization and, (2) Structure-aware Mixing.
  arXiv  Detail & Related papers  (2021-11-26T18:59:38Z)

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.