gradient-free optimization

Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models ACL 2026 Evolutionary Strategies at Scale lead to Catastrophic Forgetting ACL 2026 Black-Box Test-Time Prompt Tuning for Vision-Language Models AAAI 2025 CBP-Tuning: Efficient Local Customization for Black-box Large Language Models EMNLP 2025 Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs ACL 2025 Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition EMNLP 2025 Personalized Language Models via Privacy-Preserving Evolutionary Model Merging EMNLP 2025 PURA: Parameter Update-Recovery Test-Time Adaption for RGB-T Tracking CVPR 2025 Stein Variational Evolution Strategies UAI 2025 Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models ICLR 2025 ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think ICML 2025 Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous and Instruction-guided Driving CVPR 2024 Dual-Phase Accelerated Prompt Optimization EMNLP 2024 Exponential Hardness of Optimization from the Locality in Quantum Neural Networks AAAI 2024 FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models ICML 2024 Gradient-free Decoder Inversion in Latent Diffusion Models NeurIPS 2024 Gradient-free optimization of highly smooth functions: improved analysis and a new algorithm JMLR 2024 Improving Neural Network Generalization on Data-Limited Regression with Doubly-Robust Boosting AAAI 2024 Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives COLING 2024 Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization AAAI 2024 Multi-Scale Prompt Memory-Augmented Model for Black-Box Scenarios NAACL 2024 Personalized Federated Learning for Text Classification with Gradient-Free Prompt Tuning NAACL 2024 Accelerating Motion Planning via Optimal Transport NeurIPS 2023 GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models EACL 2023 Parameter-efficient Tuning for Large Language Model without Calculating Its Gradients EMNLP 2023