Pith. sign in

REVIEW 9 cited by

Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.02453 v1 pith:DJG3BQJT submitted 2025-03-04 cs.IR cs.AI

Yuhao Yang , Zhi Ji , Zhaopeng Li , Yi Li , Zhonglin Mo , Yue Ding , Kai Chen , Zijian Zhang
show 3 more authors
Jie Li Shuanglong Li Lin Liu
This is my paper · ORCID
classification cs.IRcs.AI
keywords densegenerativesparsecobrarepresentationsretrievalvectorscascaded
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generative models have recently gained attention in recommendation systems by directly predicting item identifiers from user interaction sequences. However, existing methods suffer from significant information loss due to the separation of stages such as quantization and sequence modeling, hindering their ability to achieve the modeling precision and accuracy of sequential dense retrieval techniques. Integrating generative and dense retrieval methods remains a critical challenge. To address this, we introduce the Cascaded Organized Bi-Represented generAtive retrieval (COBRA) framework, which innovatively integrates sparse semantic IDs and dense vectors through a cascading process. Our method alternates between generating these representations by first generating sparse IDs, which serve as conditions to aid in the generation of dense vectors. End-to-end training enables dynamic refinement of dense representations, capturing both semantic insights and collaborative signals from user-item interactions. During inference, COBRA employs a coarse-to-fine strategy, starting with sparse ID generation and refining them into dense vectors via the generative model. We further propose BeamFusion, an innovative approach combining beam search with nearest neighbor scores to enhance inference flexibility and recommendation diversity. Extensive experiments on public datasets and offline tests validate our method's robustness. Online A/B tests on a real-world advertising platform with over 200 million daily users demonstrate substantial improvements in key metrics, highlighting COBRA's practical advantages.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation

    cs.IR 2026-07 conditional novelty 6.0 of 10

    BARGE improves generative sequential recommendation by restoring item boundaries in the encoder and suppressing hierarchical semantic drift in decoding, outperforming prior generative baselines on public and industria...

  2. DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion

    cs.IR 2025-08 conditional novelty 6.0 of 10

    Masked-feature reconstruction with discrete diffusion, followed by CTR fine-tuning, improves click prediction over discriminative baselines in offline and online tests.

  3. Generative Recommendation with Semantic IDs: A Practitioner's Handbook

    cs.IR 2025-07 conditional novelty 6.0 of 10

    An open-source framework and ablation study showing which semantic-ID generative recommendation components actually matter, with results that challenge several standard defaults.

  4. EGA-V1: Unifying Online Advertising with End-to-End Learning

    cs.IR 2025-05 conditional novelty 6.0 of 10

    EGA-V1 unifies advertising ranking and auction into a single non-autoregressive generative model with cluster attention, and is reported to beat multi-stage cascades on Meituan's ad traffic.

  5. Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation

    cs.IR 2026-07 conditional novelty 5.5 of 10

    Disentangling LLM hidden states into attribute-aligned geo and semantic slots before dual-stream residual quantization cuts SID collisions and improves local-life recommendation AUC.

  6. Beyond Item Order: Temporal Gap Tokenization for Generative Recommendation with Semantic IDs

    cs.IR 2026-07 conditional novelty 5.0 of 10

    Interleaving fixed log-scale gap tokens with semantic IDs, plus TA-FAMAE temporal regularization, consistently beats ReSID and other SID generative baselines on Amazon sequential recommendation.

  7. Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation

    cs.IR 2025-06 conditional novelty 5.0 of 10

    CAR predicts each item as a chunk of semantic IDs plus a unique ID in one autoregressive step and reports large Recall@5 gains on three Amazon datasets.

  8. EGA-V2: An End-to-end Generative Framework for Industrial Advertising

    cs.IR 2025-05 conditional novelty 5.0 of 10

    EGA-V2 unifies ad ranking, creative selection, allocation, and payment into one generative transformer, and reports offline revenue and CTR improvements over cascaded and generative baselines on Meituan data.

  9. GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models

    cs.IR 2025-07 unverdicted novelty 3.0 of 10

    A survey of LLM-based generative recommendation systems, covering application settings, training pipelines, industrial deployment challenges, and future directions.

Pith tools