gradient-based optimization

Brain Tumor Growth Inversion via Differentiable Neural Surrogates MIDL 2026 Dormant Backdoor: Weaponizing Model Finetuning for Feasible Backdoor Attacks Against Pretrained Models AAAI 2026 Few-for-Many Personalized Federated Learning CVPR 2026 GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization AAAI 2026 Scalable Air-Quality Sensor Placement via Gradient-Based Mutual Information Maximization AAAI 2026 σ-zero: Gradient-based Optimization of ℓ_0-norm Adversarial Examples ICLR 2025 Accelerating Adversarial Training on Under-Utilized GPU IJCAI 2025 Controllable Memorization in LLMs via Weight Pruning EMNLP 2025 Direct Prompt Optimization with Continuous Representations ACL 2025 Diverse Rare Sample Generation with Pretrained GANs AAAI 2025 Enhancing Large Language Model Performance with Gradient-Based Parameter Selection AAAI 2025 Explaining Differences Between Model Pairs in Natural Language through Sample Learning EMNLP 2025 Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models COLING 2025 FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Data IJCAI 2025 FIDLAR: Forecast-Informed Deep Learning Architecture for Flood Mitigation AAAI 2025 G2D: Boosting Multimodal Learning with Gradient-Guided Distillation ICCV 2025 Gradient-Based Nonlinear Rehearsal Learning with Multivariate Alterations AAAI 2025 GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation NAACL 2025 GreaterPrompt: A Unified, Customizable, and High-Performing Open-Source Toolkit for Prompt Optimization ACL 2025 Gromov-Wasserstein Problem with Cyclic Symmetry CVPR 2025 Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints ACL 2025 Hierarchical Gradient-Based Genetic Sampling for Accurate Prediction of Biological Oscillations AAAI 2025 Highly Compressed Tokenizer Can Generate Without Training ICML 2025 MEDUSA: Medical Data Under Shadow Attacks via Hybrid Model Inversion AISTATS 2025 Misalignment Attack on Text-to-Image Models via Text Embedding Optimization and Inversion EMNLP 2025