Multimodal Recommendation

Follow this topic Ask about this topic

Multimodal recommendation studies how to combine interaction histories with item content to predict what users will want, especially when behavior data is sparse or items are new. Common approaches include graph-based collaborative filtering, multimodal representation alignment and fusion, temporal and sequential models, and language-model-based semantic representations. Research also explores modality routing, generative recommendation, and production settings such as feeds, shopping, music, and place discovery. A central challenge is that modalities can be noisy, missing, or in conflict, and combining them does not always improve rankings; systems must balance content signals with collaborative evidence and remain robust under changing contexts.

Latest papers

48 papers5 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Multimodal Decoupling for Diversified Recommendation through Semantic and Structural Shaping
Oct 19, 2026Changran He, Jiaming Wei, Jianghong Ma +3Recommender Systems Multimodal Recommendation
Harbin Institute of Technology(Shenzhen) Shenzhen, China · Shenzhen Key Laboratory of Internet Information Collaboration Shenzhen, China · Shenzhen Research Institute, City University of Hong Kong Shenzhen, China +1
LightCRS: Lightweight Multi-Domain Conversational Recommendation System
Oct 18, 2026He Ma, Lan You, Qiyang Wu +1Recommender Systems Multimodal Recommendation
University of Sydney Sydney, NSW, Australia · Nankai University Tianjin, China
Bridging the Topological Divide: Dual-Branch Graph Distillation with Semantic Priors for Robust Cold-Start Recommendation
Oct 14, 2026Yuanfeng QiuCold-Start Recommendation Collaborative Filtering
The Hong Kong University of Science and Technology (Guangzhou)
OT-FlowRec: Optimal Transport-Guided Multi-Bridge Flow for Multimodal Sequential Recommendation
Oct 12, 2026Miao SunRecommender Systems Multimodal Recommendation
Nanjing University of Science and Technology School of Computer Science and Engineering
Multimodal Graph Retrieval-Augmented Sequential Recommendation via Collaborative Filtering Paths
Oct 8, 2026Jason Marcell Setiadi, Xin Cao, Lina YaoRecommender Systems Sequential Recommendation
University of New South Wales, Sydney, Australia
MM-VeriRec: Failure-Guided Fusion for Verifiable Agentic Multimodal Recommendation
Sep 21, 2026Yufeng WangMultimodal Recommendation Multimodal Agents
Independent Research United States
Efficient Multimodal Generative Recommendation with Latent Narrative Reasoning
Sep 13, 2026Chenxing Wang, Nantao Zheng, Hao Miao +5Multimodal Recommendation Generative Recommendation
Weixin Group, Tencent · The Hong Kong Polytechnic University
Latent-Aligned Reasoning for Multimodal Recommendation
Sep 4, 2026Jiarui Jin, Anyang JiMultimodal Recommendation VLM Reasoning
Xiaohongshu Inc. · Nanjing University
MURAL: Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning
Sep 4, 2026Ahmad Mousavi, Majid Alikhani, Yeon-Chang Lee +2Multimodal Recommendation Multimodal Graph Learning
Department of Mathematics and Statistics American University · Independent Researcher Toronto, Ontario, Canada · Independent Researcher +4
Beyond Modality Harmony: Orthogonal Purification and Topology-Guided MoE for Conflict-Aware Multimodal Recommendation
Sep 2, 2026Jialin Liu, Zhaorui Zhang, Ray C. C. CheungRecommender Systems Multimodal Recommendation
City University of Hong Kong Hong Kong, Hong Kong · The Hong Kong Polytechnic University Hong Kong, Hong Kong
From Gradient-Boosted Trees to Deep Recommenders: Practical Lessons from Migrating a Production Customer Support Recommender
Aug 25, 2026Sonia Sharma, Jeyendran Balakrishnan, Shreya Rajpal +3Recommender Systems Learning to Rank
Intuit USA
Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation
Aug 24, 2026Naman Garg, Sarika Jain, George FazekasMusic Recommendation Multimodal Recommendation
National Institute of Technology Kurukshetra India · Queen Mary University of London United Kingdom
SA-RSQ: A Versatile Sparse Representation Framework for Multi-modal Recommender Systems
Aug 24, 2026Xiang Wang, Shigang Quan, Tingzhen Chang +5Vector Quantization Residual VQ
Tianjin University Tianjin, China · Meituan Beijing, China · Institute of Software Chinese Academy of Sciences Beijing, China
TimeRoute: Time-Aware Modality Routing and Diffusion for Multi-Modal Recommendation
Aug 11, 2026Pengyu Zhang, Yangqin Jiang, Klim Zaporojets +2Recommender Systems Multimodal Recommendation
University of Amsterdam Amsterdam, The Netherlands · University of Hong Kong Hong Kong, China · Aarhus University Aarhus, Denmark
Sequential Modality Dropout for Robust Multi-Modal Sequential Recommendation
Aug 10, 2026Guanqun Yang, Wenlong ZhangMissing-Modality Learning Multimodal Robustness
Stevens Institute of Technology Hoboken, NJ, USA
Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation
Aug 6, 2026Ziyun Xu, Bosen Ding, Yue Zhang +10LLM Reranking Recommender Systems
Meta Platforms Menlo Park, California, USA
What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems
Aug 3, 2026Zhijing Zhang, Jinpeng Yu, Xin Song +6Multimodal Recommendation Image Editing
1Qwen Business Unit of Alibaba · 2Southeast University
GALA: Generative Aligned Learning for Adaptive Multimodal Representation in the Taobao Shangou Recommender System
Jul 31, 2026Jiping Liu, Zhongmin Zhang, Zisen Sang +7Cross-Modal Alignment Multimodal Pretraining
Rajax Network Technology (Taobao Shangou of Alibaba) · Shanghai & Beijing, China · Central South University +1
PaletteID: Prototype-Composed Semantic Identifiers for Multimodal CTR Prediction
Jul 31, 2026Huanyu Liu, Baining Chen, Hui Liu +2Semantic ID Recommendation Prototype Learning
Huazhong University of Science and Technology Wuhan, Hubei, China · Central China Normal University Wuhan, Hubei, China
SlimPer: Make Personalization Model Slim and Smart
Jul 14, 2026Siqi Wang, Xianjie Chen, Shaofeng Deng +42Learning to Rank Memory-Efficient Inference
Multimodal Video-to-Music Recommendation via Semantic Retrieval and Temporal Reranking
Jul 7, 2026Seungheon Doh, Minhee Lee, Sangmoon Lee +2Cross-Modal Alignment Multimodal Embedding
Graduate School of Culture Technology, KAIST, South Korea · Gaudio Lab, Inc, South Korea
VCG: A Multimodal Retrieval Framework for E-Commerce Video Feeds under Extreme Cold-Start Conditions
Jun 17, 2026Katya Mirylenka, Egor Malykh, Mahdyar Ravanbakhsh +10Multimodal IR Cold-Start Recommendation
TU Wien, Vienna, Austria · Zalando Switzerland AG, Zurich, Switzerland · Zalando SE, Berlin, Germany
ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation
Jun 8, 2026Yihua Zhang, Mingfu Liang, Jiyan Yang +11Efficient Multimodal Inference Multimodal CoT Reasoning
Meta AI · Michigan State University · The University of North Carolina at Chapel Hill +1
Multimodal Music Recommendation System using LLMs
May 28, 2026Srikar Prabhas Kandagatla, Sreehitha R. Narayana, Chandana Magapu +6Sequential Recommendation Recommender Systems
University of Massachusetts Amherst, Massachusetts, USA · Dolby Laboratories Atlanta, Georgia, USA · Adobe Research San Jose, California, USA +2
FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation
May 20, 2026Xinhang Yuan, Zexi Huang, Anjia Cao +6Semantic ID Recommendation Cold-Start Recommendation
TikTok · ByteDance
SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
May 18, 2026Wei Chen, Xingyu Guo, Shuang Li +6Recommender Systems Multimodal Recommendation
School of Artificial Intelligence, Beihang University, Beijing, China · School of Computer Science and Engineering, Beihang University, Beijing, China
Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attacks
May 7, 2026Guanmeng Xian, Ning Yang, Philip S. YuAdversarial Training Multimodal Robustness
Sichuan University, Chengdu, China · University of Illinois at Chicago, USA
TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation
Apr 29, 2026Wei Yang, Rui Zhong, Zihan Lin +4Dynamic Graph Learning Recommender Systems
Xiaohongshu Inc. · Beijing, China
Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation
Apr 22, 2026Dongding Lin, Jian Wang, Yongqi Li +1Recommender Systems Large Language Model-Based Recommendation
Department of Computing, The Hong Kong Polytechnic University · College of Computer Science, Sichuan University
DialBGM: A Benchmark for Background Music Recommendation from Everyday Multi-Turn Dialogues
Apr 9, 2026Joonhyeok Shin, Jaehoon Kang, Yujun Lee +4Music Recommendation Recommender Systems
Sungkyunkwan University, Republic of Korea

Oct 19, 2026J/K move · Enter open · S save

Multimodal Decoupling for Diversified Recommendation through Semantic and Structural Shaping

Changran He, Jiaming Wei, Jianghong Ma, Tianjun Wei+2

Harbin Institute of Technology(Shenzhen) Shenzhen, China · Shenzhen Key Laboratory of Internet Information Collaboration Shenzhen, China · Shenzhen Research Institute, City University of Hong Kong Shenzhen, China+1

Recommender Systems Multimodal Recommendation Multimodal Disentangled Representation Learning Multimodal Graph Learning

Open paper AskPDF arXiv

Recommender systems often suffer from over-concentrated results when optimized for accuracy, limiting recommendation diversity. While diversity has become an important objective, existing methods still face fundamental limitations from both semantic and structural perspectives. On the one hand, multimodal recommender systems provide rich semantic signals, yet are often treated as auxiliary to ID embeddings, leading to ineffective semantic utilization for diversity. On the other hand, the accuracy--diversity trade-off persists during training, where accuracy gains often come at the cost of diversity. We show that this phenomenon is fundamentally governed by both the structural properties of learned representations and the dynamics of optimization. To address these challenges, we propose MOSS, a unified framework for multimodal decoupling through semantic and structural shaping. Specifically, we first introduce an MLLM-based Decoupled Feature Extraction module to disentangle multimodal content into informative representations. To enhance semantic utilization, we design a Category-aware Embedding Selection module that extracts compact, category-aware semantic features. To address structural limitations, we propose two complementary modules: Alternating Dual-Graph Propagation, which alleviates representation collapse by integrating collaborative and multimodal propagation, and Entropy-based Diversity Regularization, which mitigates optimization bias by promoting balanced category exposure. Extensive experiments on real-world datasets demonstrate that MOSS consistently achieves a superior accuracy--diversity trade-off over strong baselines.