KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning
Anzeige
Ähnliche Artikel
arXiv – cs.LG
•
CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization
arXiv – cs.AI
•
QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
arXiv – cs.AI
•
From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning
arXiv – cs.AI
•
Crucible: Quantifying the Potential of Control Algorithms through LLM Agents
arXiv – cs.AI
•
Safe and Efficient In-Context Learning via Risk Control
arXiv – cs.AI
•
LLMs revolutionieren Operations Research: Umfassende Übersicht