{"list":"other","total":103,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"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":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"2403.14403","title":"Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity","created":"2024-03-21","cited_by_count":451},{"id":"1912.13213","title":"Online Learning: A Modern Introduction Using Convex Optimization","created":"2019-12-31","cited_by_count":417},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"2005.06392","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","created":"2020-05-13","cited_by_count":264},{"id":"1801.05039","title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","created":"2018-01-15","cited_by_count":250},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"id":"1411.5908","title":"Understanding image representations by measuring their equivariance and equivalence","created":"2014-11-21","cited_by_count":243},{"id":"1402.0555","title":"Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits","created":"2014-02-04","cited_by_count":201},{"id":"2002.04926","title":"Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles","created":"2020-02-12","cited_by_count":197},{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172},{"id":"2006.11632","title":"Embedding-based Retrieval in Facebook Search","created":"2020-06-20","cited_by_count":156},{"id":"1906.01786","title":"Global Optimality Guarantees For Policy Gradient Methods","created":"2019-06-05","cited_by_count":150},{"id":"1910.03016","title":"Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?","created":"2019-10-07","cited_by_count":140},{"id":"1602.04128","title":"Coin Betting and Parameter-Free Online Learning","created":"2016-02-12","cited_by_count":133},{"id":"1802.06293","title":"Black-Box Reductions for Parameter-free Online Learning in Banach Spaces","created":"2018-02-17","cited_by_count":125},{"id":"1909.02769","title":"Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs","created":"2019-09-06","cited_by_count":118},{"id":"1904.08030","title":"Multi-Interest Network with Dynamic Routing for Recommendation at Tmall","created":"2019-04-17","cited_by_count":114},{"id":"2106.09524","title":"Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity","created":"2021-06-17","cited_by_count":110},{"id":"1803.02349","title":"Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba","created":"2018-03-06","cited_by_count":105},{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104},{"id":"1803.01088","title":"Practical Contextual Bandits with Regression Oracles","created":"2018-03-03","cited_by_count":93},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86},{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81},{"id":"1803.06971","title":"What Doubling Tricks Can and Can't Do for Multi-Armed Bandits","created":"2018-03-19","cited_by_count":71},{"id":"2206.06588","title":"Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search","created":"2022-06-14","cited_by_count":65},{"id":"1901.02470","title":"Bilinear Bandits with Low-rank Structure","created":"2019-01-08","cited_by_count":55},{"id":"1904.00242","title":"Nearly Minimax-Optimal Regret for Linearly Parameterized Bandits","created":"2019-03-30","cited_by_count":54},{"id":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52},{"id":"2006.02948","title":"Low-Rank Generalized Linear Bandit Problems","created":"2020-06-04","cited_by_count":49},{"id":"1403.0628","title":"Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and Normal Approximations","created":"2014-03-03","cited_by_count":46},{"id":"1910.06054","title":"An Optimal Algorithm for Adversarial Bandits with Arbitrary Delays","created":"2019-10-14","cited_by_count":44},{"id":"2002.00287","title":"Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits","created":"2020-02-01","cited_by_count":43},{"id":"1704.06880","title":"Misspecified Linear Bandits","created":"2017-04-23","cited_by_count":42},{"id":"1607.08254","title":"Stochastic Frank-Wolfe Methods for Nonconvex Optimization","created":"2016-07-27","cited_by_count":41},{"id":"2407.10834","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","created":"2024-07-15","cited_by_count":41},{"id":"1504.02089","title":"The Computational Power of Optimization in Online Learning","created":"2015-04-08","cited_by_count":39},{"id":"2207.04036","title":"Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent","created":"2022-07-08","cited_by_count":39},{"id":"1802.06052","title":"Online Continuous Submodular Maximization","created":"2018-02-16","cited_by_count":35},{"id":"1602.02454","title":"Efficient Algorithms for Adversarial Contextual Learning","created":"2016-02-08","cited_by_count":33},{"id":"1708.03949","title":"Gradient Methods for Submodular Maximization","created":"2017-08-13","cited_by_count":33},{"id":"1910.12424","title":"Online Continuous Submodular Maximization: From Full-Information to Bandit Feedback","created":"2019-10-28","cited_by_count":33},{"id":"1902.01903","title":"Exponentiated Gradient Meets Gradient Descent","created":"2019-02-05","cited_by_count":32},{"id":"2007.01612","title":"Online learning in MDPs with linear function approximation and bandit feedback","created":"2020-07-03","cited_by_count":30},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30},{"id":"2010.06022","title":"Adapting to Delays and Data in Adversarial Multi-Armed Bandits","created":"2020-10-12","cited_by_count":29},{"id":"2505.16037","title":"Causal LLM Routing: End-to-End Regret Minimization from Observational Data","created":"2025-05-21","cited_by_count":28},{"id":"2401.07298","title":"Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems","created":"2024-01-14","cited_by_count":20},{"id":"2104.06970","title":"Understanding the Eluder Dimension","created":"2021-04-14","cited_by_count":19},{"id":"2301.12942","title":"Refined Regret for Adversarial MDPs with Linear Function Approximation","created":"2023-01-30","cited_by_count":19},{"id":"2305.00832","title":"First- and Second-Order Bounds for Adversarial Linear Contextual Bandits","created":"2023-05-01","cited_by_count":19},{"id":"2309.00814","title":"Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits","created":"2023-09-02","cited_by_count":19},{"id":"2506.17670","title":"Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution","created":"2025-06-21","cited_by_count":19},{"id":"2201.11921","title":"Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits","created":"2022-01-28","cited_by_count":18},{"id":"1802.03386","title":"Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits","created":"2018-02-09","cited_by_count":17},{"id":"2301.13087","title":"Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation","created":"2023-01-30","cited_by_count":17},{"id":"2302.06834","title":"Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization","created":"2023-02-14","cited_by_count":15},{"id":"2409.02685","title":"RouterRetriever: Routing over a Mixture of Expert Embedding Models","created":"2024-09-04","cited_by_count":12},{"id":"2504.12883","title":"Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?","created":"2025-04-17","cited_by_count":12},{"id":"1609.01508","title":"Low-rank Bandits with Latent Mixtures","created":"2016-09-06","cited_by_count":11},{"id":"2105.13831","title":"Implicit Regularization in Matrix Sensing via Mirror Descent","created":"2021-05-28","cited_by_count":11},{"id":"2010.10168","title":"A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval","created":"2020-10-20","cited_by_count":9},{"id":"2410.03284","title":"uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs","created":"2024-10-04","cited_by_count":8},{"id":"1306.4653","title":"Multiarmed Bandits With Limited Expert Advice","created":"2013-06-19","cited_by_count":7},{"id":"2301.10500","title":"Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning","created":"2023-01-25","cited_by_count":7},{"id":"2410.07533","title":"Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification","created":"2024-10-10","cited_by_count":7},{"id":"2109.05546","title":"Improved Algorithms for Misspecified Linear Markov Decision Processes","created":"2021-09-12","cited_by_count":6},{"id":"2105.03678","title":"Nearly Minimax-Optimal Rates for Noisy Sparse Phase Retrieval via Early-Stopped Mirror Descent","created":"2021-05-08","cited_by_count":5},{"id":"2302.06355","title":"Dataset of Natural Language Queries for E-Commerce","created":"2023-02-13","cited_by_count":5},{"id":"1510.01171","title":"On the Online Frank-Wolfe Algorithms for Convex and Non-convex Optimizations","created":"2015-10-05","cited_by_count":4},{"id":"2508.11931","title":"An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction","created":"2025-08-16","cited_by_count":4},{"id":"2303.16998","title":"Does Sparsity Help in Learning Misspecified Linear Bandits?","created":"2023-03-29","cited_by_count":3},{"id":"2406.16802","title":"Improved Regret Bounds for Bandits with Expert Advice","created":"2024-06-24","cited_by_count":3}],"next_cursor":"100"}