用重正化群理论揭示全连接深度神经网络在指数族上的工作机制，为深度学习可解释性提供新视角。
arXiv:2606.00157v1 Announce Type: cross Abstract: We consider establishing the interpretability theory of deep learning through constructing a corresp…
ICML 2026接收，提出自动选择网络层检测大模型幻觉的新方法，助力提升AI可靠性。
arXiv:2605.26366v1 Announce Type: new Abstract: Recent studies on hallucination detection have shown that hallucination-related signals are more stron…
一个arXiv论文链接，助你快速了解神经网络公理化的前沿探索，适合理论研究者跟踪最新进展
arXiv:2605.20534v1 Announce Type: new Abstract: While deep neural networks have achieved remarkable success across a wide range of domains, their unde…
arXiv新论文教你评估和优化类激活映射，破解CNN解释性难题。
arXiv:2605.14641v1 Announce Type: cross Abstract: Class attribution maps (CAMs) provide local explanations for the decisions of convolutional neural n…