{"list":"other","total":59,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"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":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214},{"id":"1803.10082","title":"Efficient parametrization of multi-domain deep neural networks","created":"2018-03-27","cited_by_count":168},{"id":"2110.07577","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","created":"2021-10-14","cited_by_count":162},{"id":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144},{"id":"2212.10650","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","created":"2022-12-20","cited_by_count":133},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121},{"id":"2210.04284","title":"SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters","created":"2022-10-09","cited_by_count":83},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83},{"id":"1408.3060","title":"Fastfood: Approximate Kernel Expansions in Loglinear Time","created":"2014-08-13","cited_by_count":74},{"id":"2104.08771","title":"Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation","created":"2021-04-18","cited_by_count":74},{"id":"2301.01821","title":"Parameter-Efficient Fine-Tuning Design Spaces","created":"2023-01-04","cited_by_count":67},{"id":"2102.08597","title":"Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters","created":"2021-02-17","cited_by_count":66},{"id":"2104.08154","title":"Counter-Interference Adapter for Multilingual Machine Translation","created":"2021-04-16","cited_by_count":40},{"id":"2205.01541","title":"Efficient Fine-Tuning of BERT Models on the Edge","created":"2022-05-03","cited_by_count":29},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25},{"id":"2110.15766","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","created":"2021-10-28","cited_by_count":19},{"id":"2102.13196","title":"Named Tensor Notation","created":"2021-02-25","cited_by_count":11}],"next_cursor":null}