conftrace_
← Keywords

gradient-based optimization

191 papers

Explore in graph

Co-occurring keywords

adversarial attack (1599) gradient descent (1143) large language model (12755) few-shot learning (3390) neural network (6616) hyperparameter optimization (405) neural architecture search (665) gradient optimization (57) discrete optimization (145) multi-objective optimization (357)

Papers

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
Dormant Backdoor: Weaponizing Model Finetuning for Feasible Backdoor Attacks Against Pretrained Models AAAI 2026
Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints ACL 2025
G2D: Boosting Multimodal Learning with Gradient-Guided Distillation ICCV 2025
Hierarchical Gradient-Based Genetic Sampling for Accurate Prediction of Biological Oscillations AAAI 2025
Towards Robust Training via Gradient-Diversified Backpropagation WACV 2025
Explaining Differences Between Model Pairs in Natural Language through Sample Learning EMNLP 2025
Misalignment Attack on Text-to-Image Models via Text Embedding Optimization and Inversion EMNLP 2025
FIDLAR: Forecast-Informed Deep Learning Architecture for Flood Mitigation AAAI 2025
GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation NAACL 2025
FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Data IJCAI 2025
Accelerating Adversarial Training on Under-Utilized GPU IJCAI 2025
Enhancing Large Language Model Performance with Gradient-Based Parameter Selection AAAI 2025
Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers AAAI 2025
Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models COLING 2025
Diverse Rare Sample Generation with Pretrained GANs AAAI 2025
The Gradient of Algebraic Model Counting AAAI 2025
Direct Prompt Optimization with Continuous Representations ACL 2025
Gradient-Based Nonlinear Rehearsal Learning with Multivariate Alterations AAAI 2025
PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization ACL 2025
Controllable Memorization in LLMs via Weight Pruning EMNLP 2025
TaCOS: Task-Specific Camera Optimization with Simulation WACV 2025
YOLO-Count: Differentiable Object Counting for Text-to-Image Generation ICCV 2025
Mixtures of In-Context Learners ACL 2025