# Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale arXiv: https://arxiv.org/abs/2603.00632 ยท HTML: https://mlsanity.com/paper/2603.00632/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Builds on 27 of its 34 references that are in the map. - First posted on arXiv 28 Feb 2026. ## Builds on (most cited first, 27 of 27) - [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017) - [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016) - [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013) - [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021) - [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022) - [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021) - [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021) - [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022) - [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023) - [Self-supervised Learning with Random-projection Quantizer for Speech Recognition](https://mlsanity.com/paper/2202.01855/) (2022) - [Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders](https://mlsanity.com/paper/2210.12316/) (2022) - [Learnable Item Tokenization for Generative Recommendation](https://mlsanity.com/paper/2405.07314/) (2024) - [HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec](https://mlsanity.com/paper/2305.02765/) (2023) - [Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations](https://mlsanity.com/paper/2306.08121/) (2023) - [Restructuring Vector Quantization with the Rotation Trick](https://mlsanity.com/paper/2410.06424/) (2024) - [MTGR: Industrial-Scale Generative Recommendation Framework in Meituan](https://mlsanity.com/paper/2505.18654/) (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) - [Large Scale Product Graph Construction for Recommendation in E-commerce](https://mlsanity.com/paper/2010.05525/) (2020) - [OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search](https://mlsanity.com/paper/2509.03236/) (2025) - [Enhancing Embedding Representation Stability in Recommendation Systems with Semantic ID](https://mlsanity.com/paper/2504.02137/) (2025) - [NWT: Towards natural audio-to-video generation with representation learning](https://mlsanity.com/paper/2106.04283/) (2021) - [HiD-VAE: Interpretable Generative Recommendation via Hierarchical and Disentangled Semantic IDs](https://mlsanity.com/paper/2508.04618/) (2025) - [From Principles to Applications: A Comprehensive Survey of Discrete Tokenizers in Generation, Comprehension, Recommendation, and Information Retrieval](https://mlsanity.com/paper/2502.12448/) (2025) - [Real-time Indexing for Large-scale Recommendation by Streaming Vector Quantization Retriever](https://mlsanity.com/paper/2501.08695/) (2025) - [DAS: Dual-Aligned Semantic IDs Empowered Industrial Recommender System](https://mlsanity.com/paper/2508.10584/) (2025) - [Bridging Textual-Collaborative Gap through Semantic Codes for Sequential Recommendation](https://mlsanity.com/paper/2503.12183/) (2025) ## Built on by (most cited first, 6 of 6) - [Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations](https://mlsanity.com/paper/2606.10357/) (2026) - [A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing](https://mlsanity.com/paper/2608.04625/) (2026) - [Conditional Memory Enhanced Item Representation for Generative Recommendation](https://mlsanity.com/paper/2605.11447/) (2026) - [FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation](https://mlsanity.com/paper/2608.12845/) (2026) - [SIDScope: A Diagnostic Resource for Semantic-ID Interfaces in Generative Recommendation](https://mlsanity.com/paper/2608.18779/) (2026) - [Guiding the coarse levels of semantic IDs makes the fine levels learnable](https://mlsanity.com/paper/2609.22227/) (2026) ## Abstract (arXiv) Semantic IDs (SIDs) are compact discrete representations derived from multimodal item features, serving as a unified abstraction for ID-based and generative recommendation. However, learning high-quality SIDs remains challenging due to two issues. (1) Collision problem: the quantized token space is prone to collisions, in which semantically distinct items are assigned identical or overly similar SID compositions, resulting in semantic entanglement. (2) Collision-signal heterogeneity: collisions are not uniformly harmful. Some reflect genuine conflicts between semantically unrelated items, while others stem from benign redundancy or systematic data effects. To address these challenges, we propose Qualification-Aware Semantic ID Learning (QuaSID), an end-to-end framework that learns collision-qualified SIDs by selectively repelling qualified conflict pairs and scaling the repulsion strength by collision severity. QuaSID consists of two mechanisms: Hamming-guided Margin Repulsion, which translates low-Hamming SID overlaps into explicit, severity-scaled geometric constraints on the encoder space; and Conflict-Aware Valid Pair Masking, which masks protocol-induced benign overlaps to denoise repulsion supervision. In addition, QuaSID incorporates a dual-tower contrastive objective to inject collaborative signals into tokenization. Experiments on public benchmarks and industrial data validate QuaSID. On public datasets, QuaSID consistently outperforms strong baselines, improving top-K ranking quality by 5.9% over the best baseline while increasing SID composition diversity. In an online A/B test on Kuaishou e-commerce with a 5% traffic split, QuaSID increases ranking GMV-S2 by 2.38% and improves completed orders on cold-start retrieval by up to 6.42%. Finally, we show that the proposed repulsion loss is plug-and-play and enhances a range of SID learning frameworks across datasets.