1
What are the Right Symmetries for Formal Theorem Proving?
探讨形式定理证明中对称性的选择，为自动推理提供新视角。
arXiv:2605.22257v1 Announce Type: cross Abstract: Formal theorem provers based on large language models (LLMs) are highly sensitive to superficial var…
2
De novo design of quasisymmetric two-component protein cages
Nature发表：从头设计准对称双组分蛋白质笼，计算设计策略实现可编程尺寸与冷冻电镜验证。
Nature, Published online: 20 May 2026; doi:10.1038/s41586-026-10464-0 Researchers designed two-component proteins forming quasisymmetric cages via geo…
3
Algebraic Priors for Approximately Equivariant Networks
基于代数先验实现近似等变网络，巧妙平衡对称嵌入与架构灵活性，理论有新意。
arXiv:2506.08244v2 Announce Type: replace Abstract: Equivariant neural networks incorporate symmetries through group actions, embedding them as an ind…
4
Spontaneous symmetry breaking and Goldstone modes for deep information propagation
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…
5
The Symmetries of Three-Layer ReLU Networks
深入剖析三层ReLU网络的对称性结构，为深度学习理论提供新视角。
arXiv:2605.18319v1 Announce Type: new Abstract: We develop a framework for analyzing parameter symmetries in deep ReLU networks and obtain a complete …
6
Quotient-Space Diffusion Models
商空间扩散模型：用商空间思想巧妙处理系统对称性，实现更高效、保对称性的分子3D结构生成。
arXiv:2604.21809v2 Announce Type: replace-cross Abstract: Diffusion-based generative models have reformed generative AI, and also enabled new capabili…
7
Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry
精确对称实现困难，近似对称在指数级上更容易，这篇理论分析揭示了关键差异。
arXiv:2512.11855v2 Announce Type: replace-cross Abstract: Enforcing exact symmetry in machine learning models often yields significant gains in scient…