# From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation

arXiv: https://arxiv.org/abs/2608.21012 · HTML: https://mlsanity.com/paper/2608.21012/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 30 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 28 of 28)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Transformer Memory as a Differentiable Search Index](https://mlsanity.com/paper/2202.06991/) (2022)
- [Recommender Systems with Generative Retrieval](https://mlsanity.com/paper/2305.05065/) (2023)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [Learnable Item Tokenization for Generative Recommendation](https://mlsanity.com/paper/2405.07314/) (2024)
- [KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems](https://mlsanity.com/paper/2202.10842/) (2022)
- [Learning to Tokenize for Generative Retrieval](https://mlsanity.com/paper/2304.04171/) (2023)
- [Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations](https://mlsanity.com/paper/2503.02453/) (2025)
- [Generative Recommender with End-to-End Learnable Item Tokenization](https://mlsanity.com/paper/2409.05546/) (2024)
- [Generating Long Semantic IDs in Parallel for Recommendation](https://mlsanity.com/paper/2506.05781/) (2025)
- [OneRec-V2 Technical Report](https://mlsanity.com/paper/2508.20900/) (2025)
- [Differentiable Semantic ID for Generative Recommendation](https://mlsanity.com/paper/2601.19711/) (2026)
- [REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems](https://mlsanity.com/paper/2508.15308/) (2025)
- [Generative Retrieval with Semantic Tree-Structured Item Identifiers via Contrastive Learning](https://mlsanity.com/paper/2309.13375/) (2023)
- [LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendation](https://mlsanity.com/paper/2511.06254/) (2025)
- [Enhancing Item Tokenization for Generative Recommendation through Self-Improvement](https://mlsanity.com/paper/2412.17171/) (2024)
- [Pre-training Generative Recommender with Multi-Identifier Item Tokenization](https://mlsanity.com/paper/2504.04400/) (2025)
- [A Simple Contrastive Framework Of Item Tokenization For Generative Recommendation](https://mlsanity.com/paper/2506.16683/) (2025)
- [Decoupled Residual Quantization for Robust Semantic IDs in Recommendation](https://mlsanity.com/paper/2606.01844/) (2026)
- [Online k-means Clustering on Arbitrary Data Streams](https://mlsanity.com/paper/2102.09101/) (2021)
- [MERGE: Next-Generation Item Indexing Paradigm for Large-Scale Streaming Recommendation](https://mlsanity.com/paper/2601.20199/) (2026)
- [SSRLive: Live Streaming Recommendation with Dynamic Semantic ID](https://mlsanity.com/paper/2606.06970/) (2026)

## Abstract (arXiv)

Generative recommendation represents each item with a sequence of discrete Semantic IDs (SIDs) and predicts the sequence to retrieve the next item. Typical systems use multi-level residual quantization, which increases autoregressive decoding cost and creates a large hierarchical space that may be sparsely occupied. Static codebooks also become misaligned with current traffic as new items arrive and exposure distributions change. We propose a single-level large semantic codebook that replaces multiple residual semantic codes with one semantic token while retaining a separate collaborative disambiguation token to reduce item collisions. We further introduce an exposure-aware dynamic update mechanism based on temporal weight decay, exponential moving-average center updates, and an exposure-weighted penalty on SID changes. We also develop an offline evaluation framework covering representation quality, code utilization, cluster load, full-SID collision, and temporal stability. On two public datasets, the two-level SID improves mean Recall@10 by 5.0%-8.8% and mean NDCG@10 by 4.1%-5.1% for OneRec-V1, and by 7.1%-8.7% and 3.8%-8.5%, respectively, for OneRec-V2. Dynamic updating provides further gains on KuaiRec. Across three serving architectures, the shorter SID reduces estimated autoregressive-decoding FLOPs by 47.93%-48.70% and increases single-card QPS by 28.57%-47.0%. A five-day online A/B test serving 2.5% of production traffic improves the primary consumption metric by 0.792%.