{"total":50,"rows":[{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2410.07698","title":"Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures","created":"2024-10-10","cited_by_count":50,"area":null},{"id":"2410.08989","title":"Zeroth-Order Fine-Tuning of LLMs in Random Subspaces","created":"2024-10-11","cited_by_count":26,"area":null},{"id":"2406.18060","title":"AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning","created":"2024-06-26","cited_by_count":25,"area":null},{"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,"area":null},{"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,"area":null},{"id":"2411.10696","title":"HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization","created":"2024-11-16","cited_by_count":9,"area":null},{"id":"2509.18993","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2511.07971","title":"Low-Rank Curvature for Zeroth-Order Optimization in LLM Fine-Tuning","created":"2025-11-11","cited_by_count":7,"area":null},{"id":"2501.04287","title":"ElasticZO: A Memory-Efficient On-Device Learning with Combined Zeroth- and First-Order Optimization","created":"2025-01-08","cited_by_count":5,"area":null},{"id":"2502.03604","title":"Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training","created":"2025-02-05","cited_by_count":5,"area":null},{"id":"2505.18886","title":"KerZOO: Kernel Function Informed Zeroth-Order Optimization for Accurate and Accelerated LLM Fine-Tuning","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2501.06736","title":"ZOQO: Zero-Order Quantized Optimization","created":"2025-01-12","cited_by_count":4,"area":null},{"id":"2502.11513","title":"MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2509.05213","title":"An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2601.17261","title":"AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning","created":"2026-01-24","cited_by_count":4,"area":null},{"id":"2409.15520","title":"MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2510.00419","title":"Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2501.19099","title":"Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2502.12384","title":"Scalable Back-Propagation-Free Training of Optical Physics-Informed Neural Networks","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2510.18228","title":"Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2510.19953","title":"On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2602.02498","title":"Test-Time Detoxification without Training or Learning Anything","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2604.18264","title":"Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2505.13954","title":"VAMO: Efficient Zeroth-Order Variance Reduction for SGD with Faster Convergence","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2506.21833","title":"Memory Savings at What Cost? A Study of Alternatives to Backpropagation","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2507.07883","title":"SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2602.18181","title":"SeedFlood: A Step Toward Scalable Decentralized Fine-Tuning of LLMs","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2602.23111","title":"PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2605.18867","title":"EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2609.33548","title":"TerMeZO: Ternary Sparse Zeroth-Order Optimization for Fine-tuning BitNet Models at the Edge","created":"2026-09-27","cited_by_count":1,"area":null},{"id":"2506.17264","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2511.02757","title":"ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2601.04710","title":"Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.20422","title":"Guiding the Recommender: Information-Aware Auto-Bidding for Content Promotion","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2603.13115","title":"ZO-SAM: Zero-Order Sharpness-Aware Minimization for Efficient Sparse Training","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.24002","title":"Stochastic Dimension Zeroth-Order Estimator: Stable and Memory-Efficient Training of PINNs","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.09940","title":"New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.09034","title":"Accelerating Zeroth-Order Spectral Optimization with Partial Orthogonalization from Power Iteration","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.23180","title":"Self-Improving In-Context Learning","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.02857","title":"GRZO: Group-Relative Zeroth-Order Optimization for Large Language Model Fine-Tuning","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.14970","title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2609.10980","title":"EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at Scale","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.29446","title":"SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMM","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.37899","title":"Scaling Zero-Order Pretraining through Model Sharding","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38095","title":"Probe-Space Preconditioning for Fast and Stable Zero-Order Training","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.07553","title":"Which and When to Admit: Gradient Admission for Data-Centric Small Language Model Finetuning","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.12566","title":"Sample-Adaptive Zeroth-Order Post-Training","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.15225","title":"Zeroth-Order Fine-Tuning of LLMs in Learnable Low-Rank Subspaces","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16451","title":"StructZO: Structured Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}