{"list":"other","total":53,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"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":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"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":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"2310.08659","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","created":"2023-10-12","cited_by_count":196},{"id":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"2311.03285","title":"S-LoRA: Serving Thousands of Concurrent LoRA Adapters","created":"2023-11-06","cited_by_count":152},{"id":"2308.03303","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","created":"2023-08-07","cited_by_count":137},{"id":"2306.09782","title":"Full Parameter Fine-tuning for Large Language Models with Limited Resources","created":"2023-06-16","cited_by_count":134},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121},{"id":"1703.04813","title":"Learned Optimizers that Scale and Generalize","created":"2017-03-14","cited_by_count":110},{"id":"2402.03293","title":"Flora: Low-Rank Adapters Are Secretly Gradient Compressors","created":"2024-02-05","cited_by_count":108},{"id":"2311.12023","title":"LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning","created":"2023-11-20","cited_by_count":92},{"id":"1910.02653","title":"Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization","created":"2019-10-07","cited_by_count":91},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86},{"id":"1709.07417","title":"Neural Optimizer Search with Reinforcement Learning","created":"2017-09-21","cited_by_count":82},{"id":"2401.04151","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning","created":"2024-01-08","cited_by_count":82},{"id":"2405.17604","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","created":"2024-05-27","cited_by_count":76},{"id":"2311.09578","title":"Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying","created":"2023-11-16","cited_by_count":65},{"id":"2309.01507","title":"Memory Efficient Optimizers with 4-bit States","created":"2023-09-04","cited_by_count":54},{"id":"2406.08447","title":"The Impact of Initialization on LoRA Finetuning Dynamics","created":"2024-06-12","cited_by_count":54},{"id":"2302.11474","title":"Randomized Numerical Linear Algebra : A Perspective on the Field With an Eye to Software","created":"2023-02-22","cited_by_count":38},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38},{"id":"2209.13569","title":"Exploring Low Rank Training of Deep Neural Networks","created":"2022-09-27","cited_by_count":30},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25},{"id":"2407.07852","title":"OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training","created":"2024-07-10","cited_by_count":24},{"id":"2007.10412","title":"Randomized Automatic Differentiation","created":"2020-07-20","cited_by_count":23},{"id":"2001.08885","title":"Low-rank Gradient Approximation For Memory-Efficient On-device Training of Deep Neural Network","created":"2020-01-24","cited_by_count":20},{"id":"2406.17660","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","created":"2024-06-25","cited_by_count":18},{"id":"2402.16828","title":"Training Neural Networks from Scratch with Parallel Low-Rank Adapters","created":"2024-02-26","cited_by_count":17},{"id":"1805.08079","title":"Faster Neural Network Training with Approximate Tensor Operations","created":"2018-05-21","cited_by_count":14},{"id":"2405.16528","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","created":"2024-05-26","cited_by_count":12},{"id":"2406.10785","title":"ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation","created":"2024-06-16","cited_by_count":11},{"id":"2306.11250","title":"InRank: Incremental Low-Rank Learning","created":"2023-06-20","cited_by_count":10},{"id":"2305.15265","title":"Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model","created":"2023-05-24","cited_by_count":9},{"id":"2409.16722","title":"PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning","created":"2024-09-25","cited_by_count":5},{"id":"2201.13195","title":"Memory-Efficient Backpropagation through Large Linear Layers","created":"2022-01-31","cited_by_count":4}],"next_cursor":null}