{"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":"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2303.10512","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","created":"2023-03-18","cited_by_count":357},{"id":"2304.01933","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2023-04-04","cited_by_count":324},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269},{"id":"1509.06569","title":"Tensorizing Neural Networks","created":"2015-09-22","cited_by_count":250},{"id":"1511.06530","title":"Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications","created":"2015-11-20","cited_by_count":162},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133},{"id":"2310.18339","title":"When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications","created":"2023-10-21","cited_by_count":111},{"id":"2405.18541","title":"Low-Rank Few-Shot Adaptation of Vision-Language Models","created":"2024-05-28","cited_by_count":104},{"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":"1504.05477","title":"Randomized Block Krylov Methods for Stronger and Faster Approximate Singular Value Decomposition","created":"2015-04-21","cited_by_count":64},{"id":"2309.07439","title":"DePT: Decoupled Prompt Tuning","created":"2023-09-14","cited_by_count":58},{"id":"1611.03214","title":"Ultimate tensorization: compressing convolutional and FC layers alike","created":"2016-11-10","cited_by_count":56},{"id":"2402.02347","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","created":"2024-02-04","cited_by_count":52},{"id":"2405.15179","title":"VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks","created":"2024-05-24","cited_by_count":52},{"id":"1511.07263","title":"Input Sparsity Time Low-Rank Approximation via Ridge Leverage Score Sampling","created":"2015-11-23","cited_by_count":46},{"id":"2406.01775","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","created":"2024-06-03","cited_by_count":39},{"id":"2502.00987","title":"RandLoRA: Full-rank parameter-efficient fine-tuning of large models","created":"2025-02-03","cited_by_count":35},{"id":"2311.11501","title":"MultiLoRA: Democratizing LoRA for Better Multi-Task Learning","created":"2023-11-20","cited_by_count":32},{"id":"1711.00811","title":"Expressive power of recurrent neural networks","created":"2017-11-02","cited_by_count":30},{"id":"2310.02556","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","created":"2023-10-04","cited_by_count":29},{"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":"2410.09437","title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","created":"2024-10-12","cited_by_count":17},{"id":"2408.01008","title":"Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs","created":"2024-08-02","cited_by_count":14},{"id":"2402.11417","title":"LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models","created":"2024-02-18","cited_by_count":12},{"id":"2503.05431","title":"Quantum-PEFT: Ultra parameter-efficient fine-tuning","created":"2025-03-07","cited_by_count":11},{"id":"2408.08295","title":"SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training","created":"2024-08-15","cited_by_count":10},{"id":"2203.03366","title":"Improvements to Gradient Descent Methods for Quantum Tensor Network Machine Learning","created":"2022-03-03","cited_by_count":7},{"id":"2410.04060","title":"LoRTA: Low Rank Tensor Adaptation of Large Language Models","created":"2024-10-05","cited_by_count":7},{"id":"2506.00799","title":"Uni-LoRA: One Vector is All You Need","created":"2025-06-01","cited_by_count":7},{"id":"2402.01911","title":"From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers","created":"2024-02-02","cited_by_count":4},{"id":"2501.06300","title":"Tensorization of neural networks for improved privacy and interpretability","created":"2025-01-10","cited_by_count":3},{"id":"2406.03216","title":"Choice of PEFT Technique in Continual Learning: Prompt Tuning is Not All You Need","created":"2024-06-05","cited_by_count":2},{"id":"2504.06474","title":"FETTA: Flexible and Efficient Hardware Accelerator for Tensorized Neural Network Training","created":"2025-04-08","cited_by_count":2}],"next_cursor":null}