{"total":21,"rows":[{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114,"area":null},{"id":"2310.02025","title":"DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training","created":"2023-10-03","cited_by_count":76,"area":null},{"id":"2311.14168","title":"Fast Policy Learning for Linear Quadratic Control with Entropy Regularization","created":"2023-11-23","cited_by_count":13,"area":null},{"id":"2502.01014","title":"Refining Adaptive Zeroth-Order Optimization at Ease","created":"2025-02-03","cited_by_count":12,"area":null},{"id":"2405.19098","title":"Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior","created":"2024-05-29","cited_by_count":11,"area":null},{"id":"2308.04077","title":"Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients","created":"2023-08-08","cited_by_count":8,"area":null},{"id":"2506.14460","title":"Zeroth-Order Optimization is Secretly Single-Step Policy Optimization","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2503.12668","title":"ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory","created":"2025-03-16","cited_by_count":6,"area":null},{"id":"2502.19571","title":"LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM","created":"2025-02-26","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":"2206.07126","title":"Lazy Queries Can Reduce Variance in Zeroth-order Optimization","created":"2022-06-14","cited_by_count":2,"area":null},{"id":"2603.14254","title":"ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2507.17577","title":"Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors","created":"2025-07-23","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":"2308.00629","title":"Dependency Structure Search Bayesian Optimization for Decision Making Models","created":"2023-08-01","cited_by_count":0,"area":null},{"id":"2310.04457","title":"ProGO: Probabilistic Global Optimizer","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2407.02279","title":"How to Boost Any Loss Function","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2512.21241","title":"Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2602.13659","title":"Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2608.25116","title":"GRAPE: Gradient Refinement and Progress-Aware Exploitation for Query-Efficient High-Dimensional Bayesian Optimization","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.08277","title":"Adaptively Incorporating Directional Hints into Zeroth-Order Optimization","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}