{"list":"other","total":55,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"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":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377},{"id":"1511.06464","title":"Unitary Evolution Recurrent Neural Networks","created":"2015-11-20","cited_by_count":294},{"id":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"id":"1509.06569","title":"Tensorizing Neural Networks","created":"2015-09-22","cited_by_count":250},{"id":"2306.07280","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","created":"2023-06-12","cited_by_count":208},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133},{"id":"2212.10650","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","created":"2022-12-20","cited_by_count":133},{"id":"1804.08641","title":"Quantum generative adversarial networks","created":"2018-04-23","cited_by_count":128},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114},{"id":"2309.14859","title":"Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation","created":"2023-09-26","cited_by_count":109},{"id":"1611.00035","title":"Full-Capacity Unitary Recurrent Neural Networks","created":"2016-10-31","cited_by_count":94},{"id":"2403.17919","title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","created":"2024-03-26","cited_by_count":89},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86},{"id":"2306.07967","title":"One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning","created":"2023-06-13","cited_by_count":85},{"id":"1707.09520","title":"Orthogonal Recurrent Neural Networks with Scaled Cayley Transform","created":"2017-07-29","cited_by_count":83},{"id":"2002.01113","title":"Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform","created":"2020-02-04","cited_by_count":80},{"id":"1803.11537","title":"Towards Quantum Machine Learning with Tensor Networks","created":"2018-03-30","cited_by_count":76},{"id":"2309.02411","title":"Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices","created":"2023-09-05","cited_by_count":74},{"id":"1612.05231","title":"Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs","created":"2016-12-15","cited_by_count":65},{"id":"1810.09102","title":"Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?","created":"2018-10-22","cited_by_count":62},{"id":"1612.00188","title":"Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections","created":"2016-12-01","cited_by_count":57},{"id":"2402.02347","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","created":"2024-02-04","cited_by_count":52},{"id":"2205.13571","title":"Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations","created":"2022-05-26","cited_by_count":43},{"id":"2304.08612","title":"Bridging Discrete and Backpropagation: Straight-Through and Beyond","created":"2023-04-17","cited_by_count":31},{"id":"2405.12130","title":"MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning","created":"2024-05-20","cited_by_count":31},{"id":"2402.01376","title":"LoTR: Low Tensor Rank Weight Adaptation","created":"2024-02-02","cited_by_count":29},{"id":"2406.00132","title":"QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation","created":"2024-05-31","cited_by_count":23},{"id":"2107.03257","title":"Quantum Graph Convolutional Neural Networks","created":"2021-07-07","cited_by_count":18},{"id":"2305.00603","title":"Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation","created":"2023-04-30","cited_by_count":18},{"id":"2305.19059","title":"Geometry-aware training of factorized layers in tensor Tucker format","created":"2023-05-30","cited_by_count":12},{"id":"2403.11887","title":"SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules","created":"2024-03-18","cited_by_count":10},{"id":"2303.14844","title":"Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels","created":"2023-03-26","cited_by_count":8},{"id":"2304.06768","title":"Improving Gradient Methods via Coordinate Transformations: Applications to Quantum Machine Learning","created":"2023-04-13","cited_by_count":7},{"id":"2406.17887","title":"Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees","created":"2024-06-25","cited_by_count":7},{"id":"2102.11855","title":"Deep Unitary Convolutional Neural Networks","created":"2021-02-23","cited_by_count":2}],"next_cursor":null}