{"list":"other","total":68,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"1511.06939","title":"Session-based Recommendations with Recurrent Neural Networks","created":"2015-11-21","cited_by_count":695},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"1602.01585","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","created":"2016-02-04","cited_by_count":520},{"id":"1809.07426","title":"Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding","created":"2018-09-19","cited_by_count":476},{"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":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350},{"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":"2304.08177","title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca","created":"2023-04-17","cited_by_count":305},{"id":"2311.00176","title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","created":"2023-10-31","cited_by_count":174},{"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":"2304.03879","title":"GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation","created":"2023-04-08","cited_by_count":103},{"id":"1906.09217","title":"Hierarchical Gating Networks for Sequential Recommendation","created":"2019-06-21","cited_by_count":101},{"id":"2309.09261","title":"Leveraging Large Language Models for Sequential Recommendation","created":"2023-09-17","cited_by_count":78},{"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":"1909.02107","title":"Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems","created":"2019-09-04","cited_by_count":68},{"id":"2104.07413","title":"Empowering News Recommendation with Pre-trained Language Models","created":"2021-04-15","cited_by_count":63},{"id":"2002.11252","title":"AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations","created":"2020-02-26","cited_by_count":47},{"id":"2405.20646","title":"LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation","created":"2024-05-31","cited_by_count":47},{"id":"2101.07577","title":"Learnable Embedding Sizes for Recommender Systems","created":"2021-01-19","cited_by_count":42},{"id":"1909.11810","title":"Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems","created":"2019-09-25","cited_by_count":41},{"id":"1907.04471","title":"Neural Input Search for Large Scale Recommendation Models","created":"2019-07-10","cited_by_count":39},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35},{"id":"2007.14523","title":"Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems","created":"2020-07-28","cited_by_count":33},{"id":"2405.05219","title":"Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers","created":"2024-05-08","cited_by_count":32},{"id":"2003.01917","title":"Learning to Hash with Graph Neural Networks for Recommender Systems","created":"2020-03-04","cited_by_count":31},{"id":"2106.03373","title":"Pre-trained Language Model for Web-scale Retrieval in Baidu Search","created":"2021-06-07","cited_by_count":31},{"id":"2002.08530","title":"Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems","created":"2020-02-20","cited_by_count":24},{"id":"2310.05317","title":"Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond","created":"2023-10-09","cited_by_count":23},{"id":"1911.02079","title":"Post-Training 4-bit Quantization on Embedding Tables","created":"2019-11-05","cited_by_count":22},{"id":"2110.08190","title":"Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm","created":"2021-10-15","cited_by_count":21},{"id":"2412.06148","title":"The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity","created":"2024-12-09","cited_by_count":21},{"id":"2308.14304","title":"Solving Attention Kernel Regression Problem via Pre-conditioner","created":"2023-08-28","cited_by_count":20},{"id":"1909.05475","title":"Candidate Generation with Binary Codes for Large-Scale Top-N Recommendation","created":"2019-09-12","cited_by_count":19},{"id":"2106.02223","title":"Learning Elastic Embeddings for Customizing On-Device Recommenders","created":"2021-06-04","cited_by_count":19},{"id":"2010.11305","title":"Mixed-Precision Embedding Using a Cache","created":"2020-10-21","cited_by_count":18},{"id":"2409.19925","title":"LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation","created":"2024-09-30","cited_by_count":18},{"id":"2006.04466","title":"Differentiable Neural Input Search for Recommender Systems","created":"2020-06-08","cited_by_count":16},{"id":"2006.14827","title":"Memory-efficient Embedding for Recommendations","created":"2020-06-26","cited_by_count":15},{"id":"2203.10135","title":"Learning Compressed Embeddings for On-Device Inference","created":"2022-03-18","cited_by_count":13},{"id":"2204.03281","title":"Single-shot Embedding Dimension Search in Recommender System","created":"2022-04-07","cited_by_count":13},{"id":"2412.17316","title":"RoPE Attention Can Be Trained in Almost Linear Time","created":"2024-12-23","cited_by_count":13},{"id":"2108.11513","title":"Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer","created":"2021-08-24","cited_by_count":12},{"id":"2309.13482","title":"A Unified Scheme of ResNet and Softmax","created":"2023-09-23","cited_by_count":12},{"id":"2410.01188","title":"Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs","created":"2024-10-02","cited_by_count":12},{"id":"2109.02471","title":"Binary Code based Hash Embedding for Web-scale Applications","created":"2021-08-24","cited_by_count":11},{"id":"2004.13139","title":"A Generic Network Compression Framework for Sequential Recommender Systems","created":"2020-04-21","cited_by_count":10},{"id":"1805.02232","title":"Discrete Factorization Machines for Fast Feature-based Recommendation","created":"2018-05-06","cited_by_count":9},{"id":"2311.15390","title":"Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression","created":"2023-11-26","cited_by_count":9},{"id":"2405.12715","title":"RecGPT: Generative Pre-training for Text-based Recommendation","created":"2024-05-21","cited_by_count":9},{"id":"2410.04927","title":"FELLAS: Enhancing Federated Sequential Recommendation with LLM as External Services","created":"2024-10-07","cited_by_count":9},{"id":"2502.06167","title":"Universal Approximation of Visual Autoregressive Transformers","created":"2025-02-10","cited_by_count":9},{"id":"1903.00103","title":"Saec: Similarity-Aware Embedding Compression in Recommendation Systems","created":"2019-02-26","cited_by_count":7},{"id":"2103.06124","title":"Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems","created":"2021-02-24","cited_by_count":7},{"id":"2105.14068","title":"Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation","created":"2021-05-28","cited_by_count":7},{"id":"2310.20051","title":"The Expressibility of Polynomial based Attention Scheme","created":"2023-10-30","cited_by_count":7},{"id":"2411.00401","title":"Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory","created":"2024-11-01","cited_by_count":7},{"id":"2208.03915","title":"Dynamic Maintenance of Kernel Density Estimation Data Structure: From Practice to Theory","created":"2022-08-08","cited_by_count":6},{"id":"2112.01944","title":"Towards Low-loss 1-bit Quantization of User-item Representations for Top-K Recommendation","created":"2021-12-03","cited_by_count":2}],"next_cursor":null}