1
MANCE: Manifold Aware Concept Erasure
利用流形结构精准擦除特定概念，为AI安全与可解释性开辟新路径。
arXiv:2607.03973v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept from a representation while preserving the other infor…
2
On-Manifold Variational Learning with Heat-Kernel Priors
将热核先验引入流形变分框架，为贝叶斯深度学提供新的几何先验设计思路。
arXiv:2606.18658v1 Announce Type: new Abstract: Learning unsupervised representations of medical imaging cohorts can reveal clinically meaningful prot…
3
Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding
ICML 2026新研究用不确定性感知子空间纠正，让多模态大模型解码更可信，有效缓解流形偏离问题。
arXiv:2606.09859v1 Announce Type: cross Abstract: MLLMs frequently hallucinate objects inconsistent with visual inputs. This issue is typically attrib…
4
LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series
LLM预训练的隐藏能力：学习到的数据流形可跨模态迁移至时间序列任务，揭示通用表征机制。
arXiv:2605.20449v1 Announce Type: new Abstract: Can language-pretrained transformers become effective time-series forecasters, and why? In this paper,…
5
Riemannian Networks over Full-Rank Correlation Matrices
被ICML 2026接收，提出在全秩相关矩阵上构建黎曼网络的新几何深度学习方法。
arXiv:2605.19073v1 Announce Type: new Abstract: Representations on the Symmetric Positive Definite (SPD) manifold have garnered significant attention …
6
Manifold Random Features
探索流形上的随机特征方法，为核方法在复杂数据空间中的应用提供新思路。
arXiv:2602.03797v3 Announce Type: replace Abstract: We present a new paradigm for creating random features to approximate bi-variate functions (in par…