pith. sign in

arxiv: 2606.04448 · v1 · pith:YXMHSQV5new · submitted 2026-06-03 · 💻 cs.IR

Bridging Short Videos and Live Streams: Reasoning-Guided Multimodal LLMs for Cross-Domain Representation Learning

Le Zhang , Xiaolan Zhu , Yuchen Wang , Shilong Kang , Jiaqi Xue , Xiaoyu Zhang , Xiang Chen , Yalong Guan
show 4 more authors
Xiangyu Wu Shijun Wang Lantao Hu Kun Gai
This is my paper

Pith reviewed 2026-06-28 04:37 UTC · model grok-4.3

classification 💻 cs.IR
keywords cross-domain recommendationmultimodal large language modelsrepresentation learninglive streamingshort videosknowledge distillationcold start
0
0 comments X

The pith

Reasoning from multimodal LLMs can be distilled to create transferable representations that bridge short video and live stream recommendation domains.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that a two-stage process using multimodal large language models can transfer user interests from data-rich short videos to data-sparse live streams. In the first stage a frozen teacher MLLM produces structured cross-domain reasoning that is distilled into a lightweight student model. In the second stage this student guides decomposition of item representations into a transferable component shared across domains and a domain-residual component. The resulting representations are pre-computed offline and plugged into existing retrieval systems. Deployment results show the approach raises multiple business metrics while serving hundreds of millions of users daily.

Core claim

RGCD-Rep performs reasoning-aware distillation from a teacher MLLM into a student MLLM, then uses the student to supervise transferability-guided decomposition of item representations into transferable and domain-residual parts, enabling effective cross-domain recommendation from short videos to live streams with low deployment cost.

What carries the argument

Transferability-guided decomposition of item representations into transferable and domain-residual components, supervised by distilled MLLM cross-domain reasoning.

If this is right

  • Offline experiments demonstrate superiority over prior cross-domain methods.
  • A/B tests produce significant gains on core business metrics after deployment.
  • The framework runs at production scale serving over 400 million users daily.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same distillation-plus-decomposition pattern could reduce cold-start costs when moving data from any rich domain to a sparse one.
  • Pre-computing the decomposed representations offline may generalize to other retrieval tasks that already store item embeddings.
  • Measuring how much of the final lift comes from the reasoning step versus the decomposition step would clarify which part drives the transfer.

Load-bearing premise

Behavioral collaboration signals between short videos and live streams are sufficient to guide decomposition into transferable and domain-residual representations while the distilled student MLLM retains enough reasoning to improve retrieval.

What would settle it

An A/B test in which the student MLLM is replaced by a non-reasoning baseline and live-stream retrieval metrics show no lift would falsify the claim that the distilled reasoning is required for the observed gains.

Figures

Figures reproduced from arXiv: 2606.04448 by Jiaqi Xue, Kun Gai, Lantao Hu, Le Zhang, Shijun Wang, Shilong Kang, Xiang Chen, Xiangyu Wu, Xiaolan Zhu, Xiaoyu Zhang, Yalong Guan, Yuchen Wang.

Figure 1
Figure 1. Figure 1: Overview of the proposed RGCD-Rep framework. [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Performance comparison on tail and head items. [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Performance comparison on cold-start and active [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
read the original abstract

As live streaming services grow, many platforms offer short videos and live streams to meet diverse needs. Short videos carry substantial traffic and rich behavior signals, whereas live streaming is a core conversion scenario with sparse behavior data, making cold start severe. Transferring user interests from short videos to live streaming recommendation can alleviate these issues. Meanwhile, short videos and live streams are complex multimodal items, and integrating multimodal signals improves recommendation performance. Although Multimodal Large Language Models (MLLMs) show strong multimodal understanding and reasoning, their application to cross-domain recommendation remains underexplored. To this end, we propose Reasoning-Guided Cross-Domain Representation Learning (RGCD-Rep), a reasoning-guided framework for cross-domain recommendation from short videos to live streams. RGCD-Rep introduces MLLM reasoning resource-efficiently and learns transferable item representations guided by behavioral collaboration via two-stage training. First, reasoning-aware distillation lets a frozen teacher MLLM generate structured cross-domain reasoning knowledge and distills it into a lightweight student MLLM. Second, transferability-guided cross-domain representation learning decomposes item representations into transferable and domain residual representations. The resulting representations are computed offline and integrated into downstream retrieval tasks, enabling low-cost industrial deployment. Extensive offline experiments demonstrate RGCD-Rep's superiority. After deployment in Kuaishou's live streaming recommendation system, A/B tests show significant gains across multiple core business metrics, confirming its effectiveness and practicality in real industrial scenarios. RGCD-Rep is fully deployed and serves over 400 million users daily.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper introduces Reasoning-Guided Cross-Domain Representation Learning (RGCD-Rep) for transferring user interests from short videos to live streaming recommendation using Multimodal Large Language Models (MLLMs). It proposes a two-stage process: first, distilling reasoning knowledge from a frozen teacher MLLM to a lightweight student MLLM, and second, decomposing item representations into transferable and domain-residual parts guided by behavioral collaboration signals. The representations are used in downstream retrieval, with claims of superiority in offline experiments and significant improvements in A/B tests on Kuaishou's live streaming system, where it serves over 400 million users daily.

Significance. If the reported offline and online results hold, this work would demonstrate a practical way to leverage MLLM reasoning for cross-domain recommendation in industrial settings with sparse data in one domain, potentially improving cold-start performance in live streaming by transferring from rich short video data. The deployment at scale adds to its relevance for real-world applications.

major comments (2)
  1. [Abstract] Abstract: the abstract asserts superiority in offline experiments and significant A/B gains across core business metrics yet provides no quantitative results, error bars, baseline details, or description of how domain residual representations are learned or validated; the central claim therefore rests on uninspectable experimental outcomes.
  2. [Method] Method section (two-stage training): the description of reasoning-aware distillation and transferability-guided decomposition relies on external MLLM outputs and observed behavioral collaboration without any equations, pseudocode, or ablation metrics showing that the signals suffice to isolate transferable representations without leakage or loss of reasoning fidelity; this is load-bearing for the claim that the student MLLM preserves cross-domain reasoning.
minor comments (1)
  1. [Abstract] Abstract: the acronym RGCD-Rep is used without first spelling out 'Reasoning-Guided Cross-Domain Representation Learning'.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the abstract asserts superiority in offline experiments and significant A/B gains across core business metrics yet provides no quantitative results, error bars, baseline details, or description of how domain residual representations are learned or validated; the central claim therefore rests on uninspectable experimental outcomes.

    Authors: We agree the abstract would benefit from greater transparency. In revision we will insert concise quantitative highlights (e.g., relative lifts on key offline metrics versus strong baselines and the observed A/B gains on CTR/CVR) while preserving length limits. revision: yes

  2. Referee: [Method] Method section (two-stage training): the description of reasoning-aware distillation and transferability-guided decomposition relies on external MLLM outputs and observed behavioral collaboration without any equations, pseudocode, or ablation metrics showing that the signals suffice to isolate transferable representations without leakage or loss of reasoning fidelity; this is load-bearing for the claim that the student MLLM preserves cross-domain reasoning.

    Authors: The current manuscript describes the two-stage process at a high level. To address the concern we will add (i) explicit loss equations for reasoning-aware distillation and transferability-guided decomposition, (ii) pseudocode for the overall algorithm, and (iii) targeted ablation results that quantify how behavioral collaboration signals separate transferable from domain-residual components without degrading reasoning fidelity. revision: yes

Circularity Check

0 steps flagged

No circularity: framework relies on external MLLM distillation and observed behavioral signals with independent A/B validation

full rationale

The paper describes a two-stage process (reasoning-aware distillation from a frozen teacher MLLM followed by transferability-guided decomposition) that takes external multimodal reasoning outputs and cross-domain behavioral collaboration signals as inputs. The claimed gains are tied to offline experiments and real-world A/B tests on Kuaishou's system rather than any fitted parameter or self-referential definition. No equations, self-citations as load-bearing premises, or renamings of known results appear in the provided text. The derivation chain remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 1 invented entities

Abstract supplies no explicit free parameters, mathematical axioms, or new physical entities; the framework introduces the concepts of reasoning-aware distillation and transferable/domain-residual decomposition but provides no quantitative details on how they are implemented or validated.

invented entities (1)
  • transferable and domain residual representations no independent evidence
    purpose: Decompose item embeddings so that cross-domain knowledge can be transferred while domain-specific signals remain isolated
    Introduced in the second training stage to enable the claimed transfer from short videos to live streams

pith-pipeline@v0.9.1-grok · 5851 in / 1379 out tokens · 31276 ms · 2026-06-28T04:37:54.300863+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

39 extracted references · 26 canonical work pages

  1. [1]

    Davide Caffagni, Federico Cocchi, Luca Barsellotti, Nicholas Moratelli, Sara Sarto, Lorenzo Baraldi, Lorenzo Baraldi, Marcella Cornia, and Rita Cucchiara. 2024. The Revolution of Multimodal Large Language Models: A Survey. InFindings of the Association for Computational Linguistics: ACL 2024. doi:10.18653/v1/2024. findings-acl.807

    work page doi:10.18653/v1/2024 2024

  2. [2]

    Jiangxia Cao, Xin Cong, Jiawei Sheng, Tingwen Liu, and Bin Wang. 2022. Con- trastive Cross-Domain Sequential Recommendation. InProceedings of the 31st ACM International Conference on Information and Knowledge Management (CIKM ’22). ACM, 138–147. doi:10.1145/3511808.3557262

    work page doi:10.1145/3511808.3557262 2022

  3. [3]

    Jiangxia Cao, Ruochen Yang, Xiang Chen, Changxin Lao, Yueyang Liu, Yusheng Huang, Yuanhao Tian, Xiangyu Wu, Shuang Yang, Zhaojie Liu, and Guorui Zhou. 2026. Foresight Prediction Enhanced Live-Streaming Recommendation. In Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining (WSDM ’26). ACM. doi:10.1145/3773966.3779372

    work page doi:10.1145/3773966.3779372 2026

  4. [4]

    Jingyuan Chen, Hanwang Zhang, Xiangnan He, Liqiang Nie, Wei Liu, and Tat- Seng Chua. 2017. Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention. InProceedings of the 40th Interna- tional ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’17). Association for Computing Machiner...

    work page doi:10.1145/3077136.3080797 2017

  5. [5]

    Xu Chen, Hanxiong Chen, Hongteng Xu, Yongfeng Zhang, Yixin Cao, Zheng Qin, and Hongyuan Zha. 2019. Personalized Fashion Recommendation with Visual Explanations based on Multimodal Attention Network: Towards Visually Explainable Recommendation. InProceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval...

    arXiv 2019

  6. [6]

    Boqi Dai, Zhaocheng Du, Jieming Zhu, Jintao Xu, Deqing Zou, Quanyu Dai, Zhenhua Dong, Rui Zhang, and Hai-Tao Zheng. 2024. UniEmbedding: Learn- ing Universal Multi-Modal Multi-Domain Item Embeddings via User-View Contrastive Learning. InProceedings of the 33rd ACM International Confer- ence on Information and Knowledge Management (CIKM ’24). ACM, 4446–4453...

    work page doi:10.1145/3627673.3680098 2024

  7. [7]

    Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven C. H. Hoi. 2023. In- structBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. InAdvances in Neural Information Processing Systems, Vol. 36

    2023

  8. [8]

    Jiaxin Deng, Shiyao Wang, Yuchen Wang, Jiansong Qi, Liqin Zhao, Guorui Zhou, and Gaofeng Meng. 2024. MMBee: Live Streaming Gift-Sending Recommenda- tions via Multi-Modal Fusion and Behaviour Expansion. InProceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’24). Association for Computing Machinery, New York, NY, USA, 4...

    work page doi:10.1145/3637528.3671511 2024

  9. [9]

    Ke Guo, Changle Qu, Xiao Zhang, Liqin Zhao, Shijun Wang, Yanan Niu, and Jun Xu. 2026. Room Matters: Dynamic Room-level Collaboration Information Model- ing for Live Streaming Recommendation. InProceedings of The Web Conference

    2026

  10. [11]

    Yupeng Hou, Zhankui He, Julian McAuley, and Wayne Xin Zhao. 2023. Learn- ing Vector-Quantized Item Representation for Transferable Sequential Recom- menders. InProceedings of the ACM Web Conference 2023 (WWW ’23). Association for Computing Machinery, New York, NY, USA, 1162–1171. doi:10.1145/3543507. 3583434

    work page doi:10.1145/3543507 2023

  11. [12]

    Yupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li, Bolin Ding, and Ji-Rong Wen. 2022. Towards Universal Sequence Representation Learning for Recom- mender Systems. InProceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’22). Association for Computing Machinery, New York, NY, USA, 585–593. doi:10.1145/3534678.3539381

    work page doi:10.1145/3534678.3539381 2022

  12. [13]

    Guangneng Hu, Yu Zhang, and Qiang Yang. 2018. CoNet: Collaborative Cross Networks for Cross-Domain Recommendation. InProceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM 2018). ACM, 667–676. doi:10.1145/3269206.3271684

    work page doi:10.1145/3269206.3271684 2018

  13. [14]

    Jun Hu, Wenwen Xia, Xiaolu Zhang, Chilin Fu, Weichang Wu, Zhaoxin Huan, Ang Li, Zuoli Tang, and Jun Zhou. 2024. Enhancing Sequential Recommendation via LLM-based Semantic Embedding Learning. InProceedings of The Web Conference 2024 (WWW ’24). ACM, 103–111. doi:10.1145/3589335.3648307

    work page doi:10.1145/3589335.3648307 2024

  14. [15]

    Hanyu Li, Weizhi Ma, Peijie Sun, Jiayu Li, Cunxiang Yin, Yancheng He, Guoqiang Xu, Min Zhang, and Shaoping Ma. 2024. Aiming at the Target: Filter Collabora- tive Information for Cross-Domain Recommendation. InProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’24). ACM, 2081–2090. doi:10....

    work page doi:10.1145/3626772.3657713 2024

  15. [16]

    Hourun Li, Yifan Wang, Zhiping Xiao, Jia Yang, Changling Zhou, Ming Zhang, and Wei Ju. 2025. DisCo: graph-based disentangled contrastive learning for cold-start cross-domain recommendation. InProceedings of the AAAI Conference on Artificial Intelligence, Vol. 39. 12049–12057

    2025

  16. [17]

    Xiaodong Li, Ruochen Yang, Shuang Wen, Shen Wang, Yueyang Liu, Guoquan Wang, Weisong Hu, Qiang Luo, Jiawei Sheng, Tingwen Liu, Jiangxia Cao, Shuang Yang, and Zhaojie Liu. 2025. FARM: Frequency-Aware Model for Cross-Domain Live-Streaming Recommendation.CoRRabs/2502.09375 (2025). doi:10.48550/ arXiv.2502.09375 arXiv preprint

    arXiv 2025

  17. [18]

    Youhua Li, Hanwen Du, Yongxin Ni, Pengpeng Zhao, Qi Guo, Fajie Yuan, and Xiaofang Zhou. 2024. Multi-Modality is All You Need for Transferable Recom- mender Systems. In2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 5008–5021. doi:10.1109/ICDE60146.2024.00380

    work page doi:10.1109/icde60146.2024.00380 2024

  18. [19]

    Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruc- tion Tuning. InAdvances in Neural Information Processing Systems, Vol. 36

    2023

  19. [20]

    Lihao Liu, Yan Wang, Biao Yang, Da Li, Jiangxia Cao, Yuxiao Luo, Xiang Chen, Xiangyu Wu, Wei Yuan, Fan Yang, Guiguang Ding, Tingting Gao, and Guorui Zhou. 2026. CREM: Compression-Driven Representation Enhancement for Mul- timodal Retrieval and Comprehension.arXiv preprint arXiv:2602.19091(2026). https://arxiv.org/abs/2602.19091 arXiv:2602.19091

    arXiv 2026

  20. [21]

    Meng Liu, Jianjun Li, Guohui Li, and Peng Pan. 2020. Cross Domain Recommen- dation via Bi-directional Transfer Graph Collaborative Filtering Networks. In Proceedings of the 29th ACM International Conference on Information and Knowl- edge Management (CIKM ’20). ACM, 885–894. doi:10.1145/3340531.3412012

    work page doi:10.1145/3340531.3412012 2020

  21. [22]

    Haokai Ma, Ruobing Xie, Lei Meng, Xin Chen, Xu Zhang, Leyu Lin, and Jie Zhou. 2024. Triple Sequence Learning for Cross-domain Recommendation.ACM Transactions on Information Systems42, 4, Article 91 (2024), 91:1–91:29 pages. doi:10.1145/3638351

    work page doi:10.1145/3638351 2024

  22. [23]

    Tong Man, Huawei Shen, Xiaolong Jin, and Xueqi Cheng. 2017. Cross-Domain Recommendation: An Embedding and Mapping Approach. InProceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17). IJCAI Organization, 2464–2470. doi:10.24963/ijcai.2017/343

    work page doi:10.24963/ijcai.2017/343 2017

  23. [24]

    Rongqing Kenneth Ong and Andy W. H. Khong. 2025. Spectrum-based Modality Representation Fusion Graph Convolutional Network for Multimodal Recom- mendation. InProceedings of the Eighteenth ACM International Conference on Web Search and Data Mining (WSDM ’25). Association for Computing Machinery, New York, NY, USA, 773–781. doi:10.1145/3701551.3703561

    work page doi:10.1145/3701551.3703561 2025

  24. [25]

    Chung Park, Taesan Kim, Taekyoon Choi, Junui Hong, Yelim Yu, Mincheol Cho, Kyunam Lee, Sungil Ryu, Hyungjun Yoon, Minsung Choi, and Jaegul Choo

  25. [26]

    InProceedings of the 32nd ACM International Conference on Information and Knowledge Management

    Cracking the Code of Negative Transfer: A Cooperative Game Theoretic Approach for Cross-Domain Sequential Recommendation. InProceedings of the 32nd ACM International Conference on Information and Knowledge Management. 2024–2033. doi:10.1145/3583780.3614828

    work page doi:10.1145/3583780.3614828 2024

  26. [27]

    Changle Qu, Liqin Zhao, Yanan Niu, Xiao Zhang, and Jun Xu. 2025. Bridging Short Videos and Streamers with Multi-Graph Contrastive Learning for Live Streaming Recommendation. InProceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’25). ACM, 2059–2069. doi:10.1145/3726302.3729914

    work page doi:10.1145/3726302.3729914 2025

  27. [28]

    Qwen Team. 2026. Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All. https://qwen.ai/blog?id=qwen3.6-35b-a3b

    2026

  28. [29]

    Leheng Sheng, An Zhang, Yi Zhang, Yuxin Chen, Xiang Wang, and Tat-Seng Chua

  29. [30]

    InThe Thirteenth International Conference on Learning Representations

    Language Representations Can be What Recommenders Need: Findings and Potentials. InThe Thirteenth International Conference on Learning Representations. https://openreview.net/forum?id=eIJfOIMN9z

  30. [31]

    Jinpeng Wang, Ziyun Zeng, Yunxiao Wang, Yuting Wang, Xingyu Lu, Tianxiang Li, Jun Yuan, Rui Zhang, Hai-Tao Zheng, and Shu-Tao Xia. 2023. MISSRec: Pre- training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation. InProceedings of the 31st ACM International Conference on Multimedia (MM ’23). Association for Computing Mach...

    work page doi:10.1145/3581783.3611967 2023

  31. [32]

    Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model’s Perception of the World at Any Resolution.arXiv preprint arXiv:2409.12191(2024)

    Pith/arXiv arXiv 2024

  32. [33]

    Yinwei Wei, Xiang Wang, Liqiang Nie, Xiangnan He, and Tat-Seng Chua. 2020. GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback. InProceedings of the 28th ACM International Conference on Multimedia (MM ’20). Association for Computing Machinery, New York, NY, USA, 3541–3549. doi:10.1145/3394171.3413556

    work page doi:10.1145/3394171.3413556 2020

  33. [34]

    Yinwei Wei, Xiang Wang, Liqiang Nie, Xiangnan He, Richang Hong, and Tat-Seng Chua. 2019. MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video. InProceedings of the 27th ACM International Conference on Multimedia (MM ’19). Association for Computing Machinery, New York, NY, USA, 1437–1445. doi:10.1145/3343031.3351034

    work page doi:10.1145/3343031.3351034 2019

  34. [35]

    Ruobing Xie, Qi Liu, Liangdong Wang, Shukai Liu, Bo Zhang, and Leyu Lin. 2022. Contrastive Cross-Domain Recommendation in Matching. InProceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’22). ACM, 4226–4236. doi:10.1145/3534678.3539125

    work page doi:10.1145/3534678.3539125 2022

  35. [36]

    Wei Yang, Jie Yang, and Yuan Liu. 2023. Multimodal Optimal Transport Knowl- edge Distillation for Cross-domain Recommendation. InProceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM ’23). ACM, 2959–2968. doi:10.1145/3583780.3614983 Bridging Short Videos and Live Streams Conference acronym ’XX, June 03–05, 2018...

    work page doi:10.1145/3583780.3614983 2023

  36. [37]

    Yuyang Ye, Zhi Zheng, Yishan Shen, Tianshu Wang, Hengruo Zhang, Peijun Zhu, Runlong Yu, Kai Zhang, and Hui Xiong. 2025. Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation. InProceedings of the AAAI Conference on Artificial Intelligence, Vol. 39. 13069–13077. doi:10.1609/ aaai.v39i12.33426

    2025

  37. [38]

    Chuang Zhao, Hongke Zhao, Ming He, Jian Zhang, and Jianping Fan. 2023. Cross-domain recommendation via user interest alignment. InProceedings of The Web Conference 2023 (WWW ’23). ACM, 887–896. doi:10.1145/3543507.3583263

    work page doi:10.1145/3543507.3583263 2023

  38. [39]

    Xin Zhou and Zhiqi Shen. 2023. A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation. InProceedings of the 31st ACM International Conference on Multimedia (MM ’23). Association for Computing Machinery, New York, NY, USA, 935–943. doi:10.1145/3581783.3611943

    work page doi:10.1145/3581783.3611943 2023

  39. [40]

    Yongchun Zhu, Kaikai Ge, Fuzhen Zhuang, Ruobing Xie, Dongbo Xi, Xu Zhang, Leyu Lin, and Qing He. 2022. Personalized Transfer of User Preferences for Cross-domain Recommendation. InProceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. 1507–1515. doi:10.1145/3488560. 3498388

    work page doi:10.1145/3488560 2022