Cost-Sensitive Unbiased Risk Estimation for Multi-Class Positive-Unlabeled Learning
"实验验证" 相关文章
From Black-box to Causal-box: Towards Building More Interpretable Models
A Framework for Quantifying How Pre-Training and Context Benefit In-Context Learning
On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
Competition and Diversity in Generative AI
Rethinking Cross-lingual Gaps from a Statistical Viewpoint
Practical, Utilitarian Algorithm Configuration
AOAD-MAT: Transformer-based multi-agent deep reinforcement learning model considering agents' order of action decisions
Fake News in Social Networks
Local Mechanisms of Compositional Generalization in Conditional Diffusion
How Easter Island’s giant statues “walked” to their final platforms
Structured Cognition for Behavioral Intelligence in Large Language Model Agents: Preliminary Study
Does Using Counterfactual Help LLMs Explain Textual Importance in Classification?
Train Once, Answer All: Many Pretraining Experiments for the Cost of One
Dual-Space Smoothness for Robust and Balanced LLM Unlearning
$K$-Level Policy Gradients for Multi-Agent Reinforcement Learning
Neural Video Compression with In-Loop Contextual Filtering and Out-of-Loop Reconstruction Enhancement
A Computational Method for Measuring "Open Codes" in Qualitative Analysis
史上最著名的物理实验，为啥伽利略根本不用做
