{"list":"other","total":80,"rows":[{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1808.09781","title":"Self-Attentive Sequential Recommendation","created":"2018-08-20","cited_by_count":1184},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"1506.04757","title":"Image-based Recommendations on Styles and Substitutes","created":"2015-06-15","cited_by_count":706},{"id":"1511.06939","title":"Session-based Recommendations with Recurrent Neural Networks","created":"2015-11-21","cited_by_count":695},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"2203.13366","title":"Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)","created":"2022-03-24","cited_by_count":402},{"id":"2305.00447","title":"TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation","created":"2023-04-30","cited_by_count":337},{"id":"2008.07873","title":"S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization","created":"2020-08-18","cited_by_count":311},{"id":"2305.08845","title":"Large Language Models are Zero-Shot Rankers for Recommender Systems","created":"2023-05-15","cited_by_count":309},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300},{"id":"2305.05065","title":"Recommender Systems with Generative Retrieval","created":"2023-05-08","cited_by_count":198},{"id":"2304.10149","title":"Is ChatGPT a Good Recommender? A Preliminary Study","created":"2023-04-20","cited_by_count":193},{"id":"2402.17152","title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","created":"2024-02-27","cited_by_count":188},{"id":"1812.07617","title":"Towards Deep Conversational Recommendations","created":"2018-12-18","cited_by_count":176},{"id":"2502.18965","title":"OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment","created":"2025-02-26","cited_by_count":173},{"id":"2305.07001","title":"Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach","created":"2023-05-11","cited_by_count":168},{"id":"2305.02182","title":"Uncovering ChatGPT's Capabilities in Recommender Systems","created":"2023-05-03","cited_by_count":161},{"id":"2205.08084","title":"M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems","created":"2022-05-17","cited_by_count":152},{"id":"1510.01784","title":"VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback","created":"2015-10-06","cited_by_count":151},{"id":"2306.05817","title":"How Can Recommender Systems Benefit from Large Language Models: A Survey","created":"2023-06-09","cited_by_count":142},{"id":"2410.02712","title":"LLaVA-Critic: Learning to Evaluate Multimodal Models","created":"2024-10-03","cited_by_count":134},{"id":"2303.13835","title":"Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited","created":"2023-03-24","cited_by_count":124},{"id":"2206.05941","title":"Towards Universal Sequence Representation Learning for Recommender Systems","created":"2022-06-13","cited_by_count":121},{"id":"1808.05163","title":"A Simple Convolutional Generative Network for Next Item Recommendation","created":"2018-08-15","cited_by_count":120},{"id":"1908.05391","title":"Towards Knowledge-Based Recommender Dialog System","created":"2019-08-15","cited_by_count":113},{"id":"2210.12316","title":"Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders","created":"2022-10-22","cited_by_count":112},{"id":"2405.11273","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","created":"2024-05-18","cited_by_count":108},{"id":"2304.03879","title":"GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation","created":"2023-04-08","cited_by_count":103},{"id":"2305.06569","title":"How to Index Item IDs for Recommendation Foundation Models","created":"2023-05-11","cited_by_count":102},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88},{"id":"1901.07555","title":"Managing Popularity Bias in Recommender Systems with Personalized Re-ranking","created":"2019-01-22","cited_by_count":82},{"id":"2308.08434","title":"A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems","created":"2023-08-16","cited_by_count":73},{"id":"2304.03516","title":"Generative Recommendation: Towards Next-generation Recommender Paradigm","created":"2023-04-07","cited_by_count":70},{"id":"2311.01343","title":"Collaborative Large Language Model for Recommender Systems","created":"2023-11-02","cited_by_count":64},{"id":"2403.19021","title":"IDGenRec: LLM-RecSys Alignment with Textual ID Learning","created":"2024-03-27","cited_by_count":53},{"id":"2505.18654","title":"MTGR: Industrial-Scale Generative Recommendation Framework in Meituan","created":"2025-05-24","cited_by_count":49},{"id":"2305.14302","title":"VIP5: Towards Multimodal Foundation Models for Recommendation","created":"2023-05-23","cited_by_count":46},{"id":"2502.06788","title":"EVEv2: Improved Baselines for Encoder-Free Vision-Language Models","created":"2025-02-10","cited_by_count":41},{"id":"2404.17591","title":"Large Language Models for Next Point-of-Interest Recommendation","created":"2024-04-19","cited_by_count":40},{"id":"2312.02443","title":"E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendation","created":"2023-12-05","cited_by_count":39},{"id":"2305.11700","title":"Exploring the Upper Limits of Text-Based Collaborative Filtering Using Large Language Models: Discoveries and Insights","created":"2023-05-19","cited_by_count":38},{"id":"2404.18465","title":"M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework","created":"2024-04-29","cited_by_count":32},{"id":"2308.11175","title":"MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation","created":"2023-08-22","cited_by_count":31},{"id":"2009.13724","title":"One Person, One Model, One World: Learning Continual User Representation without Forgetting","created":"2020-09-29","cited_by_count":30},{"id":"2305.15036","title":"Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights","created":"2023-05-24","cited_by_count":29},{"id":"2206.06190","title":"TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback","created":"2022-06-13","cited_by_count":27},{"id":"2111.11294","title":"Scaling Law for Recommendation Models: Towards General-purpose User Representations","created":"2021-11-15","cited_by_count":26},{"id":"2304.05263","title":"Prompt Learning for News Recommendation","created":"2023-04-11","cited_by_count":25},{"id":"2405.02429","title":"CALRec: Contrastive Alignment of Generative LLMs for Sequential Recommendation","created":"2024-05-03","cited_by_count":24},{"id":"2403.05063","title":"Aligning Large Language Models for Controllable Recommendations","created":"2024-03-08","cited_by_count":19},{"id":"2404.00245","title":"Aligning Large Language Models with Recommendation Knowledge","created":"2024-03-30","cited_by_count":19},{"id":"2406.00033","title":"Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Tracking","created":"2024-05-25","cited_by_count":18},{"id":"2102.10989","title":"UPRec: User-Aware Pre-training for Recommender Systems","created":"2021-02-22","cited_by_count":16},{"id":"2408.05430","title":"HoME: Hierarchy of Multi-Gate Experts for Multi-Task Learning at Kuaishou","created":"2024-08-10","cited_by_count":16},{"id":"2412.15341","title":"Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models","created":"2024-12-19","cited_by_count":16},{"id":"2502.14137","title":"Collaborative Retrieval for Large Language Model-based Conversational Recommender Systems","created":"2025-02-19","cited_by_count":16},{"id":"2506.07371","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","created":"2025-06-09","cited_by_count":16},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16},{"id":"2306.17256","title":"Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendations","created":"2023-06-29","cited_by_count":15},{"id":"2305.04518","title":"Sparks of Artificial General Recommender (AGR): Early Experiments with ChatGPT","created":"2023-05-08","cited_by_count":13},{"id":"2406.12042","title":"Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models","created":"2024-06-17","cited_by_count":13},{"id":"2504.05314","title":"Multimodal Quantitative Language for Generative Recommendation","created":"2025-02-20","cited_by_count":12},{"id":"2009.09226","title":"Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect","created":"2020-09-19","cited_by_count":11},{"id":"2305.05973","title":"Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models","created":"2023-05-10","cited_by_count":10},{"id":"2012.07598","title":"StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking","created":"2020-12-14","cited_by_count":6},{"id":"2502.03604","title":"Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training","created":"2025-02-05","cited_by_count":5},{"id":"2502.03041","title":"Large Language Model as Universal Retriever in Industrial-Scale Recommender System","created":"2025-02-05","cited_by_count":4},{"id":"2405.19612","title":"Keyword-driven Retrieval-Augmented Large Language Models for Cold-start User Recommendations","created":"2024-05-30","cited_by_count":3},{"id":"2506.19993","title":"CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems","created":"2025-06-24","cited_by_count":3},{"id":"2505.01695","title":"SimAug: Enhancing Recommendation with Pretrained Language Models for Dense and Balanced Data Augmentation","created":"2025-05-03","cited_by_count":2}],"next_cursor":null}