{"list":"other","total":55,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"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":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"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":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"2303.10512","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","created":"2023-03-18","cited_by_count":357},{"id":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"id":"2312.03732","title":"A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA","created":"2023-11-28","cited_by_count":243},{"id":"1812.04754","title":"Gradient Descent Happens in a Tiny Subspace","created":"2018-12-12","cited_by_count":217},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192},{"id":"1806.03884","title":"Fast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis","created":"2018-06-11","cited_by_count":146},{"id":"1602.01407","title":"A Kronecker-factored approximate Fisher matrix for convolution layers","created":"2016-02-03","cited_by_count":141},{"id":"2306.09782","title":"Full Parameter Fine-tuning for Large Language Models with Limited Resources","created":"2023-06-16","cited_by_count":134},{"id":"2310.17813","title":"A Spectral Condition for Feature Learning","created":"2023-10-26","cited_by_count":109},{"id":"2402.03293","title":"Flora: Low-Rank Adapters Are Secretly Gradient Compressors","created":"2024-02-05","cited_by_count":108},{"id":"2406.08446","title":"OLMES: A Standard for Language Model Evaluations","created":"2024-06-12","cited_by_count":106},{"id":"2410.21265","title":"Modular Duality in Deep Learning","created":"2024-10-28","cited_by_count":77},{"id":"2405.14813","title":"Scalable Optimization in the Modular Norm","created":"2024-05-23","cited_by_count":68},{"id":"2406.17748","title":"A New Perspective on Shampoo's Preconditioner","created":"2024-06-25","cited_by_count":59},{"id":"2309.01507","title":"Memory Efficient Optimizers with 4-bit States","created":"2023-09-04","cited_by_count":54},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38},{"id":"2307.02047","title":"CAME: Confidence-guided Adaptive Memory Efficient Optimization","created":"2023-07-05","cited_by_count":36},{"id":"2008.01425","title":"PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning","created":"2020-08-04","cited_by_count":35},{"id":"2502.15015","title":"Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition","created":"2025-02-20","cited_by_count":32},{"id":"2310.10195","title":"AdaLomo: Low-memory Optimization with Adaptive Learning Rate","created":"2023-10-16","cited_by_count":31},{"id":"2011.04720","title":"Improving Neural Network Training in Low Dimensional Random Bases","created":"2020-11-09","cited_by_count":19},{"id":"2405.15593","title":"MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence","created":"2024-05-24","cited_by_count":19},{"id":"2302.03764","title":"Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions","created":"2023-02-07","cited_by_count":17},{"id":"2410.17881","title":"AdaRankGrad: Adaptive Gradient-Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning","created":"2024-10-23","cited_by_count":17},{"id":"2304.05187","title":"Automatic Gradient Descent: Deep Learning without Hyperparameters","created":"2023-04-11","cited_by_count":14},{"id":"2502.06742","title":"Gradient Multi-Normalization for Stateless and Scalable LLM Training","created":"2025-02-10","cited_by_count":9},{"id":"2403.14958","title":"Adapprox: Adaptive Approximation in Adam Optimization via Randomized Low-Rank Matrices","created":"2024-03-22","cited_by_count":8}],"next_cursor":null}