Artificial Inductive Bias for Synthetic Tabular Data Generation in Data-Scarce Scenarios
"元学习" 相关文章
Clustering by Attention: Leveraging Prior Fitted Transformers for Data Partitioning
Anomaly Detection in Human Language via Meta-Learning: A Few-Shot Approach
How Should We Meta-Learn Reinforcement Learning Algorithms?
Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs
Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
Domain Generalization via Pareto Optimal Gradient Matching
Proficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models
CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labels
Meta-Reinforcement Learning for Fast and Data-Efficient Spectrum Allocation in Dynamic Wireless Networks
Meta-Learning Transformers to Improve In-Context Generalization
75%预训练数据都能删！Jeff Dean新作：全自动筛除低质量数据
75%预训练数据都能删！Jeff Dean新作：全自动筛除低质量数据
75%预训练数据都能删，Jeff Dean新作：全自动筛除低质量数据
揭秘LLM“思考”之谜：推理即“梯度下降”，元学习框架解构训练过程，还给优化提供新思路
大模型何以擅长小样本学习？ICLR 2025这项研究给出详细分析
Nat. Commun. | 赋能不对称催化选择性预测的元学习框架
苹果专利革新手势识别：解决少样本学习难题，个性化视觉交互更智能
Few-Shot Preference Optimization (FSPO): A Novel Machine Learning Framework Designed to Model Diverse Sub-Populations in Preference Datasets to Elicit Personalization in Language Models for Open-Ended Question Answering
Putting the Smarts into Robot Bodies
