任务无关持续学习新范式，稀疏子空间与专家共享高效应对灾难性遗忘
arXiv:2606.07500v1 Announce Type: cross Abstract: Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, …
探究晶体管老化如何影响深度学习模型，并提出长期与短期老化的缓解策略，硬件与AI交叉的前沿研究。
arXiv:2606.04266v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are used in a variety of real-world applications including, for example,…
Transformer一致性训练机制，通过堆叠层间约束提升模型表现与稳定性。
arXiv:2606.05817v1 Announce Type: cross Abstract: Consistency training encourages models to behave similarly across different contexts, and has shown …
颠覆深度缩放传统认知：层间相似性导致“越深越差”的逆缩放现象，ICML 2026最新发现。
arXiv:2602.05970v2 Announce Type: replace Abstract: Neural scaling laws relate loss to model size in large language models (LLMs), yet depth and width…
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…
对抗性补丁从数字仿真到现实世界的转移，空中目标检测鲁棒性面临新挑战
arXiv:2606.00159v1 Announce Type: cross Abstract: Deep neural network (DNN)-based object detectors are widely used for analyzing aerial and satellite …
颠覆传统：无需深度神经网络的大语言模型新架构，带来性能提升与具体案例验证。
arXiv:2605.30385v1 Announce Type: cross Abstract: The purpose of this article is to provide validation to my deep neural network alternative in the co…
提出轻量级选择器捕捉logit shift趋势，高效平衡持续学习中的“可塑-稳定”矛盾
arXiv:2605.27469v1 Announce Type: cross Abstract: Continual Learning (CL) is a practical paradigm to utilize power of deep pre-trained neural networks…
深度神经网络公平性修复新突破，提供可证明保证，已被ASE 2025录用。
arXiv:2605.19549v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are suffering from ethical issues such as individual discrimination. In …
深度神经网络泛化理论新视角，揭示点态泛化机制，突破传统平均泛化分析局限。
arXiv:2605.18598v1 Announce Type: new Abstract: We address the fundamental question of why deep neural networks generalize by establishing a pointwise…
用物理对称性破缺理论解释深层网络信息传播，提出Goldstone类似模式实现长距离相干传递，前沿交叉理论。
arXiv:2605.14685v1 Announce Type: cross Abstract: In physical systems, whenever a continuous symmetry is spontaneously broken, the system possesses ex…