{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740},{"id":"1703.04247","title":"DeepFM: A Factorization-Machine based Neural Network for CTR Prediction","created":"2017-03-13","cited_by_count":676},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674},{"id":"1908.07442","title":"TabNet: Attentive Interpretable Tabular Learning","created":"2019-08-20","cited_by_count":648},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"1407.7722","title":"OpenML: networked science in machine learning","created":"2014-07-29","cited_by_count":526},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2012.06678","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","created":"2020-12-11","cited_by_count":409},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"2004.13912","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","created":"2020-04-29","cited_by_count":319},{"id":"2106.01342","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","created":"2021-06-02","cited_by_count":319},{"id":"2306.00297","title":"Transformers learn to implement preconditioned gradient descent for in-context learning","created":"2023-06-01","cited_by_count":279},{"id":"2305.02997","title":"When Do Neural Nets Outperform Boosted Trees on Tabular Data?","created":"2023-05-04","cited_by_count":223},{"id":"1909.06312","title":"Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data","created":"2019-09-13","cited_by_count":203},{"id":"1708.03731","title":"OpenML Benchmarking Suites","created":"2017-08-11","cited_by_count":178},{"id":"2007.04074","title":"Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning","created":"2020-07-08","cited_by_count":174},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98},{"id":"2305.06090","title":"XTab: Cross-table Pretraining for Tabular Transformers","created":"2023-05-10","cited_by_count":81},{"id":"2307.14338","title":"TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023","created":"2023-07-26","cited_by_count":74},{"id":"2406.05207","title":"Retrieval & Fine-Tuning for In-Context Tabular Models","created":"2024-06-07","cited_by_count":59},{"id":"2112.02962","title":"DANets: Deep Abstract Networks for Tabular Data Classification and Regression","created":"2021-12-06","cited_by_count":50},{"id":"2402.11137","title":"TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks","created":"2024-02-17","cited_by_count":47},{"id":"2405.16156","title":"Mixture of In-Context Prompters for Tabular PFNs","created":"2024-05-25","cited_by_count":33},{"id":"2308.06912","title":"CausalLM is not optimal for in-context learning","created":"2023-08-14","cited_by_count":26},{"id":"2402.14335","title":"HyperFast: Instant Classification for Tabular Data","created":"2024-02-22","cited_by_count":22},{"id":"2408.06291","title":"Mambular: A Sequential Model for Tabular Deep Learning","created":"2024-08-12","cited_by_count":21},{"id":"2402.06971","title":"In-Context Data Distillation with TabPFN","created":"2024-02-10","cited_by_count":19},{"id":"2406.07368","title":"When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models","created":"2024-06-11","cited_by_count":9},{"id":"2310.19572","title":"Improving Input-label Mapping with Demonstration Replay for In-context Learning","created":"2023-10-30","cited_by_count":2}],"next_cursor":null}