{"total":28,"rows":[{"id":"2404.02059","title":"IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT","created":"2024-04-02","cited_by_count":26,"area":null},{"id":"2402.05355","title":"A Survey on Safe Multi-Modal Learning System","created":"2024-02-08","cited_by_count":15,"area":null},{"id":"2508.15281","title":"MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2411.02992","title":"Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation","created":"2024-11-05","cited_by_count":7,"area":null},{"id":"2512.07216","title":"MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling","created":"2025-12-08","cited_by_count":6,"area":null},{"id":"2505.16376","title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2512.16891","title":"LinkedOut: Linking World Knowledge Representation Out of Video LLM for Next-Generation Video Recommendation","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2405.00287","title":"SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation","created":"2024-05-01","cited_by_count":4,"area":null},{"id":"2407.05610","title":"Described Spatial-Temporal Video Detection","created":"2024-07-08","cited_by_count":3,"area":null},{"id":"2503.05493","title":"Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation","created":"2025-03-07","cited_by_count":3,"area":null},{"id":"2502.12945","title":"LLMPopcorn: Exploring LLMs as Assistants for Popular Micro-video Generation","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2508.05709","title":"G-UBS: Towards Robust Understanding of Implicit Feedback via Group-Aware User Behavior Simulation","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2508.06154","title":"Semantic Item Graph Enhancement for Multimodal Recommendation","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2509.03131","title":"RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation","created":"2025-09-03","cited_by_count":2,"area":null},{"id":"2409.08543","title":"ATFLRec: A Multimodal Recommender System with Audio-Text Fusion and Low-Rank Adaptation via Instruction-Tuned Large Language Model","created":"2024-09-13","cited_by_count":1,"area":null},{"id":"2411.15455","title":"M3TR: Temporal Retrieval Enhanced Multi-Modal Micro-video Popularity Prediction","created":"2024-11-23","cited_by_count":1,"area":null},{"id":"2508.05667","title":"ITDR: An Instruction Tuning Dataset for Enhancing Large Language Models in Recommendations","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2510.26095","title":"ORBIT -- Open Recommendation Benchmark for Reproducible Research with Hidden Tests","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2604.26252","title":"OmniTrend: Content-Context Modeling for Scalable Social Popularity Prediction","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2409.12396","title":"ARTAI: An Evaluation Platform to Assess Societal Risk of Recommender Algorithms","created":"2024-09-19","cited_by_count":0,"area":null},{"id":"2503.06238","title":"Token-Efficient Item Representation via Images for LLM Recommender Systems","created":"2025-03-08","cited_by_count":0,"area":null},{"id":"2508.16170","title":"EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendation","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2602.20723","title":"Modality-Guided Mixture of Structured Experts with Entropy-Triggered Routing for Multimodal Recommendation","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.02137","title":"NextAds: Towards Next-generation Personalized Video Advertising","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2605.08810","title":"Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2608.15055","title":"TAHB: A Comprehensive Benchmark for Text-Attributed Hypergraph Learning","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.00996","title":"Does This Moment Justify the Recommendation? Counterfactual Behavior-Grounded Evidence Retrieval for Personalized Video Recommendation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.14487","title":"AlignPoison: Conditional Targeted Poisoning of Generative Recommenders via Decoding-Aligned Prefixes","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}