# BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendation

arXiv: https://arxiv.org/abs/2504.06636 · HTML: https://mlsanity.com/paper/2504.06636/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2025.

## Built on by (most cited first, 5 of 5)

- [PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations](https://mlsanity.com/paper/2510.07784/) (2025)
- [S2GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation](https://mlsanity.com/paper/2601.18664/) (2026)
- [DMGIN: How Multimodal LLMs Enhance Large Recommendation Models for Lifelong User Post-click Behaviors](https://mlsanity.com/paper/2508.21801/) (2025)
- [PRISM: Purified Representation and Integrated Semantic Modeling for Generative Sequential Recommendation](https://mlsanity.com/paper/2601.16556/) (2026)
- [ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping](https://mlsanity.com/paper/2606.31693/) (2026)

## Abstract (arXiv)

Multi-modal sequential recommendation systems leverage auxiliary signals (e.g., text, images) to alleviate data sparsity in user-item interactions. While recent methods exploit large language models to encode modalities into discrete semantic IDs for autoregressive prediction, we identify two critical limitations: (1) Existing approaches adopt fragmented quantization, where modalities are independently mapped to semantic spaces misaligned with behavioral objectives, and (2) Over-reliance on semantic IDs disrupts inter-modal semantic coherence, thereby weakening the expressive power of multi-modal representations for modeling diverse user preferences. To address these challenges, we propose a Behavior-Bind multi-modal Quantization for Sequential Recommendation (BBQRec for short) featuring dual-aligned quantization and semantics-aware sequence modeling. First, our behavior-semantic alignment module disentangles modality-agnostic behavioral patterns from noisy modality-specific features through contrastive codebook learning, ensuring semantic IDs are inherently tied to recommendation tasks. Second, we design a discretized similarity reweighting mechanism that dynamically adjusts self-attention scores using quantized semantic relationships, preserving multi-modal synergies while avoiding invasive modifications to the sequence modeling architecture. Extensive evaluations across four real-world benchmarks demonstrate BBQRec's superiority over the state-of-the-art baselines.