{"list":"other","total":64,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1708.03999","title":"ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models","created":"2017-08-14","cited_by_count":666},{"id":"1804.08598","title":"Black-box Adversarial Attacks with Limited Queries and Information","created":"2018-04-23","cited_by_count":501},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193},{"id":"2006.06224","title":"A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning","created":"2020-06-11","cited_by_count":162},{"id":"1805.11770","title":"AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks","created":"2018-05-30","cited_by_count":137},{"id":"1807.04457","title":"Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach","created":"2018-07-12","cited_by_count":130},{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114},{"id":"1805.10367","title":"Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization","created":"2018-05-25","cited_by_count":111},{"id":"2505.16932","title":"The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm","created":"2025-05-22","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":"2406.09044","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","created":"2024-06-13","cited_by_count":94},{"id":"1910.06513","title":"ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization","created":"2019-10-15","cited_by_count":76},{"id":"2310.02025","title":"DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training","created":"2023-10-03","cited_by_count":76},{"id":"2505.13416","title":"Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)","created":"2025-05-19","cited_by_count":72},{"id":"2402.15751","title":"Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning","created":"2024-02-24","cited_by_count":54},{"id":"2402.15173","title":"Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer","created":"2024-02-23","cited_by_count":53},{"id":"2410.07698","title":"Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures","created":"2024-10-10","cited_by_count":50},{"id":"1910.12166","title":"Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization","created":"2019-10-27","cited_by_count":47},{"id":"2203.14195","title":"How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective","created":"2022-03-27","cited_by_count":39},{"id":"2408.12857","title":"Memory-Efficient LLM Training with Online Subspace Descent","created":"2024-08-23","cited_by_count":39},{"id":"2510.16981","title":"MuonBP: Faster Muon via Block-Periodic Orthogonalization","created":"2025-10-19","cited_by_count":35},{"id":"2410.11289","title":"Subspace Optimization for Large Language Models with Convergence Guarantees","created":"2024-10-15","cited_by_count":34},{"id":"2406.02913","title":"Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity","created":"2024-06-05","cited_by_count":28},{"id":"2410.08989","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","created":"2024-10-11","cited_by_count":26},{"id":"2012.11148","title":"Efficient On-Chip Learning for Optical Neural Networks Through Power-Aware Sparse Zeroth-Order Optimization","created":"2020-12-21","cited_by_count":24},{"id":"2512.05117","title":"The Universal Weight Subspace Hypothesis","created":"2025-12-04","cited_by_count":24},{"id":"2403.02993","title":"Localized Zeroth-Order Prompt Optimization","created":"2024-03-05","cited_by_count":23},{"id":"1710.07804","title":"Zeroth-Order Online Alternating Direction Method of Multipliers: Convergence Analysis and Applications","created":"2017-10-21","cited_by_count":22},{"id":"1907.11684","title":"On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method","created":"2019-07-26","cited_by_count":21},{"id":"2107.03941","title":"Zeroth order optimization with orthogonal random directions","created":"2021-07-08","cited_by_count":21},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20},{"id":"2505.24749","title":"SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training","created":"2025-05-30","cited_by_count":19},{"id":"2502.03304","title":"Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning","created":"2025-02-05","cited_by_count":18},{"id":"2509.11983","title":"Low-rank Orthogonalization for Large-scale Matrix Optimization with Applications to Foundation Model Training","created":"2025-09-15","cited_by_count":18},{"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":"2502.07222","title":"A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models","created":"2025-02-11","cited_by_count":16},{"id":"2506.09034","title":"FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed","created":"2025-06-10","cited_by_count":14},{"id":"2510.19975","title":"Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations","created":"2025-10-22","cited_by_count":11},{"id":"2504.20314","title":"Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training","created":"2025-04-28","cited_by_count":9},{"id":"2506.04430","title":"Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order","created":"2025-06-04","cited_by_count":9},{"id":"2401.13944","title":"Zeroth-order Random Subspace Algorithm for Non-smooth Convex Optimization","created":"2024-01-25","cited_by_count":6},{"id":"2509.15552","title":"The Multi-Query Paradox in Zeroth-Order Optimization","created":"2025-09-19","cited_by_count":4},{"id":"2405.04765","title":"When Foresight Pruning Meets Zeroth-Order Optimization: Efficient Federated Learning for Low-Memory Devices","created":"2024-05-08","cited_by_count":2}],"next_cursor":null}