information theory
A field that deals with quantifying information, often used in AI to measure the efficiency of algorithms and the capacity of models to store and process information.
- Enhancing Privacy in Multimodal Federated Learning with Information Theory
- Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning
- Information-Theoretic Reward Decomposition for Generalizable RLHF
- Long-Tailed Recognition via Information-Preservable Two-Stage Learning
- Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization
- Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
- Neural Entropy
- Tight Bounds for Answering Adaptively Chosen Concentrated Queries
- Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models