Density-Ratio Rescoring for Imbalanced Classification
该研究通过密度比重评分(DRR)方法解决不平衡分类问题,利用调查整合法对多数样本重新加权,并结合基础分类器提高稀有类排名的精度。
该研究通过密度比重评分(DRR)方法解决不平衡分类问题,利用调查整合法对多数样本重新加权,并结合基础分类器提高稀有类排名的精度。
为解决矩阵图模型中估计不对称和参数选择困难问题,提出了一种联合估计偏相关的方法,改善了图恢复性能。
为解决大模型生成代码的安全性问题,MACGen通过多代理协作进行规划、安全分析、代码合成与优化,以提高代码的功能正确性和安全性。
This study addresses the reliance on character-specific data and labor-intensive rigging in arbitrary 3D speech animation generation by proposing a zero-animation-data-driven paradigm. The method leverages a video diffusion model to convert talking-head videos into 3D animations, employing character-specific fine-tuning to preserve motion priors. Furthermore, it integrates blendshape parameter optimization with knowledge distillation to construct a real-time inference network. This approach achieves cross-mesh, zero-shot 3D lip-sync generation without requiring any 3D training data. By eliminating the need for 3D datasets, the proposed framework significantly reduces manual annotation costs while maintaining real-time performance, thereby offering an efficient solution for universal 3D speech animation.
This work addresses the performance limitations of existing isogeny-based key exchange protocols, which remain viable despite the cryptanalysis of SIDH and its variants via classical polynomial-time key recovery attacks. We present the first adaptation of the high-dimensional isogeny-based POKE public-key encryption scheme into a key encapsulation mechanism suitable for key exchange. A systematic performance evaluation at NIST security level 1 demonstrates that our POKE-based key exchange significantly outperforms current isogeny-based alternatives: it achieves approximately 21.21× speedup over terSIDH and 64.97× over CSIDH. These results establish POKE as a highly promising candidate for post-quantum key exchange, offering both strong security foundations and markedly improved efficiency.
该研究通过密度比重评分(DRR)方法解决不平衡分类问题,利用调查整合法对多数样本重新加权,并结合基础分类器提高稀有类排名的精度。
为解决矩阵图模型中估计不对称和参数选择困难问题,提出了一种联合估计偏相关的方法,改善了图恢复性能。
为解决大模型生成代码的安全性问题,MACGen通过多代理协作进行规划、安全分析、代码合成与优化,以提高代码的功能正确性和安全性。
This study addresses the reliance on character-specific data and labor-intensive rigging in arbitrary 3D speech animation generation by proposing a zero-animation-data-driven paradigm. The method leverages a video diffusion model to convert talking-head videos into 3D animations, employing character-specific fine-tuning to preserve motion priors. Furthermore, it integrates blendshape parameter optimization with knowledge distillation to construct a real-time inference network. This approach achieves cross-mesh, zero-shot 3D lip-sync generation without requiring any 3D training data. By eliminating the need for 3D datasets, the proposed framework significantly reduces manual annotation costs while maintaining real-time performance, thereby offering an efficient solution for universal 3D speech animation.
This work addresses the performance limitations of existing isogeny-based key exchange protocols, which remain viable despite the cryptanalysis of SIDH and its variants via classical polynomial-time key recovery attacks. We present the first adaptation of the high-dimensional isogeny-based POKE public-key encryption scheme into a key encapsulation mechanism suitable for key exchange. A systematic performance evaluation at NIST security level 1 demonstrates that our POKE-based key exchange significantly outperforms current isogeny-based alternatives: it achieves approximately 21.21× speedup over terSIDH and 64.97× over CSIDH. These results establish POKE as a highly promising candidate for post-quantum key exchange, offering both strong security foundations and markedly improved efficiency.