{"list":"other","total":79,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1808.09781","title":"Self-Attentive Sequential Recommendation","created":"2018-08-20","cited_by_count":1184},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"1603.09320","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","created":"2016-03-30","cited_by_count":861},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"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":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1706.06978","title":"Deep Interest Network for Click-Through Rate Prediction","created":"2017-06-21","cited_by_count":544},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1809.07426","title":"Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding","created":"2018-09-19","cited_by_count":476},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"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":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2407.19669","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval","created":"2024-07-29","cited_by_count":236},{"id":"1609.02132","title":"UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory","created":"2016-09-07","cited_by_count":200},{"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":"2311.09049","title":"Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation","created":"2023-11-15","cited_by_count":179},{"id":"1804.07931","title":"Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate","created":"2018-04-21","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":"2006.11632","title":"Embedding-based Retrieval in Facebook Search","created":"2020-06-20","cited_by_count":156},{"id":"1904.08918","title":"Attentive Single-Tasking of Multiple Tasks","created":"2019-04-18","cited_by_count":148},{"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":"2405.07314","title":"Learnable Item Tokenization for Generative Recommendation","created":"2024-05-12","cited_by_count":110},{"id":"1906.09217","title":"Hierarchical Gating Networks for Sequential Recommendation","created":"2019-06-21","cited_by_count":101},{"id":"2310.19488","title":"CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation","created":"2023-10-30","cited_by_count":100},{"id":"1801.02294","title":"Learning Tree-based Deep Model for Recommender Systems","created":"2018-01-08","cited_by_count":99},{"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":"2304.04171","title":"Learning to Tokenize for Generative Retrieval","created":"2023-04-09","cited_by_count":68},{"id":"2409.12740","title":"HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling","created":"2024-09-19","cited_by_count":63},{"id":"2406.14017","title":"EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration","created":"2024-06-20","cited_by_count":58},{"id":"2403.19021","title":"IDGenRec: LLM-RecSys Alignment with Textual ID Learning","created":"2024-03-27","cited_by_count":53},{"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":"1902.07565","title":"Joint Optimization of Tree-based Index and Deep Model for Recommender Systems","created":"2019-02-19","cited_by_count":37},{"id":"2007.12329","title":"Long-tail Session-based Recommendation","created":"2020-07-24","cited_by_count":33},{"id":"2408.09698","title":"Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation","created":"2024-08-19","cited_by_count":33},{"id":"2408.10159","title":"Customizing Language Models with Instance-wise LoRA for Sequential Recommendation","created":"2024-08-19","cited_by_count":32},{"id":"2301.12618","title":"ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning","created":"2023-01-30","cited_by_count":28},{"id":"2411.11739","title":"QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou","created":"2024-11-18","cited_by_count":28},{"id":"2206.06190","title":"TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback","created":"2022-06-13","cited_by_count":27},{"id":"2006.15408","title":"Learning Optimal Tree Models Under Beam Search","created":"2020-06-27","cited_by_count":26},{"id":"2404.14774","title":"CoST: Contrastive Quantization based Semantic Tokenization for Generative Recommendation","created":"2024-04-23","cited_by_count":26},{"id":"2405.03988","title":"LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application","created":"2024-05-07","cited_by_count":21},{"id":"2206.09672","title":"Adaptive Domain Interest Network for Multi-domain Recommendation","created":"2022-06-20","cited_by_count":20},{"id":"2411.18814","title":"Unifying Generative and Dense Retrieval for Sequential Recommendation","created":"2024-11-27","cited_by_count":18},{"id":"2108.05060","title":"MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning using an Anchor Free Approach","created":"2021-08-11","cited_by_count":17},{"id":"2407.21022","title":"A Comprehensive Survey on Retrieval Methods in Recommender Systems","created":"2024-07-11","cited_by_count":16},{"id":"2202.10226","title":"Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation","created":"2022-02-14","cited_by_count":14},{"id":"2306.04039","title":"Revisiting Neural Retrieval on Accelerators","created":"2023-06-06","cited_by_count":14},{"id":"2007.07203","title":"Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations","created":"2020-07-12","cited_by_count":11},{"id":"2405.10835","title":"A Unified Search and Recommendation Framework Based on Multi-Scenario Learning for Ranking in E-commerce","created":"2024-05-17","cited_by_count":3},{"id":"2410.09560","title":"Towards Scalable Semantic Representation for Recommendation","created":"2024-10-12","cited_by_count":3},{"id":"2410.16080","title":"Unleashing the Potential of Multi-Channel Fusion in Retrieval for Personalized Recommendations","created":"2024-10-21","cited_by_count":3}],"next_cursor":null}