From the 3 of 65 papers with an AI index.
184 citations
- Sun Yat-sen UniversityCN5 papers
- Beijing Electronic Science and Technology InstituteCN4 papers
- Chinese Academy of SciencesCN4 papers
- Tsinghua UniversityCN4 papers
- Beihang UniversityCN3 papers
- Hong Kong Polytechnic UniversityHK3 papers
- Shanghai Jiao Tong UniversityCN3 papers
- University of Hong KongHK3 papers
- China Mobile (China)CN2 papers
- Guangxi UniversityCN2 papers
- Institut de Recherche et d’InnovationFR2 papers
- Shandong Institute of AutomationCN2 papers
56 papers
Quantized Spin Hall Effect in Three-Dimensional Nodal-Ring Semimetal: Geometric Scaling and Symmetry-Engineered Spin Response
Jiali Chen, Chaoxi Cui, Zhi-Ming Yu +2
The anomalous Hall conductivity in magnetic Weyl semimetals scales linearly with the momentum separation between Weyl nodes, establishing a geometric paradigm for three-dimensional…
SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification
Wenyao Cui, Huaping Zhang, Yongyi Huang +6
Large language models (LLMs) increasingly serve as data-driven reasoners, yet their chains-of-thought (CoT) can be unfaithful even when final answers are correct. Most existing ``v…
Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework
Zhaoqi Wang, Daqing He, Zijian Zhang +13
While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption att…
3D Topologically Polarized Elastic Metamaterials Enable Asymmetric Energy Isolation at Low Frequencies
Shaoyuan Zhang, Xuejian Gong, Fangyuan Ma +5
Topologically polarized elasticity has been extensively studied in lower-dimensions, yet its three-dimensional (3D) counterpart remains largely unexplored. Here, we demonstrate omn…
A Robust EDM Optimization Approach for 3D Single-Source Localization with Angle and Range Measurements
Mingyu Zhao, Qingna Li, Hou-Duo Qi
The paper proposes a robust Euclidean distance matrix optimization method that jointly uses range and angle data with an L1-norm criterion to improve 3D single-source localization…
Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation
Kun Fang, Qinghua Tao, Mingzhen He +6
The paper proposes a kernel PCA based method for out-of-distribution detection that learns a discriminative non-linear subspace using a newly designed Cosine-Gaussian kernel and in…