No article text was recorded for this version.
zeroth-order gradient estimation (activation-free optimization)
Version 2 of 297 papers131 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory
- Blog: On the Convergence of Zeroth-Order Federated Tuning for Large Language Models
- Blog: MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines
- Blog: PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs
- Blog: On the Inherent Privacy of Zeroth-Order Projected Gradient Descent
- Blog: Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches
- Blog: More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning
- Blog: SubZero: Composing Subject, Style, and Action via Zero-Shot Personalization
- Blog: SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes
- Blog: Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach
- Blog: Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes
- Blog: New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework
- Blog: Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning
- Blog: Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models
- Blog: Communication-Efficient Byzantine-Resilient Federated Zero-Order Optimization
- Blog: Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches
- Blog: Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approach
- Blog: Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
- Blog: End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost
- Blog: Real-Time FJ/MAC PDE Solvers via Tensorized, Back-Propagation-Free Optical PINN Training
- Blog: Zero-th Order Algorithm for Softmax Attention Optimization
- Blog: Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning
- Blog: ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
- Blog: Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes
- Blog: FwdLLM: Efficient Federated Finetuning of Large Language Models with Perturbed Inferences
- Blog: Fine-Tuning Language Models with Just Forward Passes
- Blog: Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models
- Blog: Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models
- Blog: Synergizing Foundation Models and Federated Learning: A Survey
- Blog: H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models
- Blog: Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations
- Blog: PSO-Merging: Merging Models Based on Particle Swarm Optimization
- Blog: More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning
- Blog: Enabling Resource-Efficient On-Device Fine-Tuning of LLMs Using Only Inference Engines
- Blog: Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models
- Blog: ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-Order Optimization
- Blog: Zeroth-Order Sharpness-Aware Learning with Exponential Tilting
- Blog: Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
- Blog: Hybrid Decentralized Optimization: First- and Zeroth-Order Optimizers Can Be Jointly Leveraged For Faster Convergence
- Blog: ComPO: Preference Alignment via Comparison Oracles
- Blog: Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
- Blog: Zeroth-Order Optimization Finds Flat Minima
- Blog: Revisiting Consistency for Semi-Supervised Semantic Segmentation
- Blog: ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory
- Blog: Memory-Efficient Personalization of Text-to-Image Diffusion Models via Selective Optimization Strategies
- Blog: Zeroth-Order Forward-Only SNN Training Inspiring Neuromorphic On-Chip Learning
- Blog: Communication and Energy Efficient Federated Learning using Zero-Order Optimization Technique
- Blog: MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba
- Blog: AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning
- Blog: MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs
- Blog: Query-Efficient Zeroth-Order Algorithms for Nonconvex Optimization
- Blog: Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models
- Blog: Stepping Forward on the Last Mile
- Blog: Zeroth-Order Fine-Tuning of LLMs in Random Subspaces
- Blog: AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments
- Blog: EA4LLM: A Gradient-Free Approach to Large Language Model Optimization via Evolutionary Algorithms
- Blog: BAFFLE: A Baseline of Backpropagation-Free Federated Learning
- Blog: CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
- Blog: ReLIZO: Sample Reusable Linear Interpolation-based Zeroth-order Optimization
- Blog: Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models
Showing 60 of 97 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_zeroth_order_gradient_estimation_activat_7ccdf55c,
title = {zeroth-order gradient estimation (activation-free optimization)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/zeroth-order-gradient-estimation-activation-free-optimization/rdr_7ccdf55cd1154773a1a213744baf0c40},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_zeroth_order_gradient_estimation_activat_7ccdf55c_v2,
title = {zeroth-order gradient estimation (activation-free optimization)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/zeroth-order-gradient-estimation-activation-free-optimization/rdr_7ccdf55cd1154773a1a213744baf0c40/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}