PulseAugur
EN
LIVE 12:37:32

New research explores advanced generative recommendation systems

Researchers are exploring advanced generative recommendation systems that move beyond traditional methods. Several papers introduce novel architectures and techniques to improve personalization, efficiency, and the handling of various data modalities like text and images. These new models aim to better capture user intent, address issues like popularity bias, and integrate diverse information sources for more effective and interpretable recommendations. AI

IMPACT These advancements in generative recommendation systems could lead to more personalized and efficient user experiences across various platforms.

RANK_REASON Multiple arXiv papers introduce new models and techniques for generative recommendation systems.

Read on arXiv cs.IR (Information Retrieval) →

AI-generated summary · Google Gemini · from 15 sources. How we write summaries →

COVERAGE [15]

  1. arXiv cs.LG TIER_1 English(EN) · Yangchen Zeng, Zhenyu Yu, Zhiyuan Hu, Wenxin Zhang, Jinze Wang, Rongfeng Guo ·

    DeepInterestGR: Mining Deep Multi-Interest Using Multi-Modal LLMs for Generative Recommendation

    arXiv:2602.18907v2 Announce Type: replace Abstract: We introduce DeepInterestGR, a novel framework that integrates deep interest mining into the generative recommendation pipeline. This addresses the "Shallow Interest" problem - existing generative methods rely on surface-level t…

  2. arXiv cs.AI TIER_1 English(EN) · Jun Yin, Bangguo Zhu, Peng Huo, Ruochen Liu, Hao Chen, Senzhang Wang, Shirui Pan, Chengqi Zhang ·

    Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenders

    arXiv:2605.16825v2 Announce Type: replace-cross Abstract: Recently, Generative Recommenders (GRs), characterized by a unified end-to-end framework, have exhibited astonishing potential in transforming the recommendation paradigm. Despite their effectiveness, we recognize that GRs…

  3. arXiv cs.AI TIER_1 English(EN) · Pingjun Pan, Tingting Zhou, Peiyao Lu, Tingting Fei, Hongxiang Chen, Chuanjiang Luo ·

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

    arXiv:2602.11799v2 Announce Type: replace 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)…

  4. arXiv cs.AI TIER_1 English(EN) · Pingjun Pan, Tingting Zhou, Peiyao Lu, Tingting Fei, Hongxiang Chen, Chuanjiang Luo ·

    L2Rec: Towards Dual-View Understanding of LLMs for Personalized Recommendation

    arXiv:2605.26717v1 Announce Type: cross Abstract: Adapting large language models (LLMs) for personalized recommendation requires aligning their general-purpose capabilities with user-specific preferences while effectively leveraging both behavioral and semantic signals. Existing …

  5. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Chuanjiang Luo ·

    L2Rec: Towards Dual-View Understanding of LLMs for Personalized Recommendation

    Adapting large language models (LLMs) for personalized recommendation requires aligning their general-purpose capabilities with user-specific preferences while effectively leveraging both behavioral and semantic signals. Existing approaches typically integrate these signals at ei…

  6. arXiv cs.AI TIER_1 Dansk(DA) · Chaotian Song, Jingyao Zhang, Chenghao Chen, Zisen Sang, Dehai Zhao, Guodong Cao, Boxi Wu, Deng Cai, Jia Jia ·

    DeGRe: Dense-supervised Generative Reranking for Recommendation

    arXiv:2605.25749v1 Announce Type: cross Abstract: In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space…

  7. arXiv cs.AI TIER_1 Dansk(DA) · Jia Jia ·

    DeGRe: Dense-supervised Generative Reranking for Recommendation

    In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent studies have shifted towards end-to-end g…

  8. Hugging Face Daily Papers TIER_1 Dansk(DA) ·

    DeGRe: Dense-supervised Generative Reranking for Recommendation

    In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent studies have shifted towards end-to-end g…

  9. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Jeremiah D. Deng ·

    How Reliable Are Semantic-ID Tokenizer Comparisons in Generative Recommendation?

    In Semantic-ID (SID) based generative recommendation, each item is represented as a sequence of discrete codes, and an autoregressive model is trained to generate the SID sequence of the next item; top-K performance is then measured by checking whether the SID sequence of the tar…

  10. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Moumita Bhattacharya ·

    Towards Generalizable and Efficient Large-Scale Generative Recommenders

    Generative recommendation models can model user behavior as sequences of events and provide a shared backbone for multiple recommendation tasks. In production, however, pre-training gains do not automatically translate into downstream application improvements: task headroom, repe…

  11. arXiv cs.IR (Information Retrieval) TIER_1 Dansk(DA) · Cheng Long ·

    Generative Conversational Recommender System

    Conversational recommender systems aim to provide personalized recommendations via natural language interactions. However, existing approaches either decouple recommendation from dialog generation or rely on retrieval-based pipelines, limiting the integration between recommendati…

  12. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Fuzhen Zhuang ·

    SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation

    Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over item identifiers. Recent studies have incorporated multimodal signals to provide richer token-level evidence for generation. Howeve…

  13. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Yunshan Ma ·

    Dual-Diffusional Generative Fashion Recommendation

    Personalized generative recommender systems have emerged as a promising solution for fashion recommendation. However, existing methods primarily rely on implicit visual embeddings from historical interactions, which often contain preference-irrelevant information and result in in…

  14. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Xianneng Li ·

    RAGR: Review-Augmented Generative Recommendation

    Sequential recommendation (SR) is traditionally formulated as next-item prediction over a chronological sequence of interacted items. Although recent generative recommendation (GR) methods introduce new machinery, such as semantic IDs, autoregressive decoding, and unified token s…

  15. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Chengqi Zhang ·

    Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenders

    Recently, Generative Recommenders (GRs), characterized by a unified end-to-end framework, have exhibited astonishing potential in transforming the recommendation paradigm. Despite their effectiveness, we recognize that GRs are still susceptible to the long-standing issue of popul…