MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration
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。
0 citationsRead paper
Selected work
Representative Papers
AnyTalk: Speech Animation for Arbitrary Characters Leveraging a Video Generation Model
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.
0 citationsRead paper
POKEx: Performance analysis of POKE-key exchange and SIDH-variants
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.
0 citationsRead paper
Censored broken adaptive ridge rank regression via induced smoothing
This study addresses the challenge of variable selection and parameter estimation in high-dimensional survival data with right-censoring and partially interval-censoring, particularly when covariates are highly correlated. The authors propose a linear rank regression approach for the accelerated failure time model that integrates Broken Adaptive Ridge (BAR) penalty with induced smoothing. This method, the first to incorporate BAR into a smoothed rank regression framework, enjoys the oracle property and grouping effect, accommodates multivariate partial interval censoring, and yields closed-form variance estimates. Computationally efficient implementation is achieved via a cyclic coordinate descent algorithm. Simulation studies demonstrate its superior performance over existing methods in both variable selection accuracy and estimation efficiency. The approach has been successfully applied to clinical datasets on primary biliary cirrhosis and colorectal cancer, and the accompanying R package aftPenCDA is publicly available on CRAN.
0 citationsRead paper
Eigen for Statistical and Machine Learning Computing: A Lightweight C++ Tutorial with Python Bindings
This work addresses the gap between algorithmic prototypes and efficient implementations in scientific research by proposing a lightweight approach to translate statistical and machine learning algorithms—such as kernel ridge regression and stochastic gradient descent matrix factorization—from mathematical formulations into readable, high-performance C++ code. Leveraging the Eigen template library for core linear algebra operations—including kernel matrix construction, regularized solvers, and vectorized updates—the implementation seamlessly integrates into the Python ecosystem via pybind11, enabling efficient interoperability with NumPy arrays. The project provides concise, reproducible code examples that encapsulate common computational patterns in research, significantly lowering the barrier for researchers to adopt C++ for high-performance development while balancing performance, readability, and usability.
0 citationsRead paper
Recent publications
Latest Papers
MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration
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。
0 citationsRead paper
AnyTalk: Speech Animation for Arbitrary Characters Leveraging a Video Generation Model
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.
0 citationsRead paper
POKEx: Performance analysis of POKE-key exchange and SIDH-variants
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.
0 citationsRead paper
Censored broken adaptive ridge rank regression via induced smoothing
This study addresses the challenge of variable selection and parameter estimation in high-dimensional survival data with right-censoring and partially interval-censoring, particularly when covariates are highly correlated. The authors propose a linear rank regression approach for the accelerated failure time model that integrates Broken Adaptive Ridge (BAR) penalty with induced smoothing. This method, the first to incorporate BAR into a smoothed rank regression framework, enjoys the oracle property and grouping effect, accommodates multivariate partial interval censoring, and yields closed-form variance estimates. Computationally efficient implementation is achieved via a cyclic coordinate descent algorithm. Simulation studies demonstrate its superior performance over existing methods in both variable selection accuracy and estimation efficiency. The approach has been successfully applied to clinical datasets on primary biliary cirrhosis and colorectal cancer, and the accompanying R package aftPenCDA is publicly available on CRAN.
0 citationsRead paper
Eigen for Statistical and Machine Learning Computing: A Lightweight C++ Tutorial with Python Bindings
This work addresses the gap between algorithmic prototypes and efficient implementations in scientific research by proposing a lightweight approach to translate statistical and machine learning algorithms—such as kernel ridge regression and stochastic gradient descent matrix factorization—from mathematical formulations into readable, high-performance C++ code. Leveraging the Eigen template library for core linear algebra operations—including kernel matrix construction, regularized solvers, and vectorized updates—the implementation seamlessly integrates into the Python ecosystem via pybind11, enabling efficient interoperability with NumPy arrays. The project provides concise, reproducible code examples that encapsulate common computational patterns in research, significantly lowering the barrier for researchers to adopt C++ for high-performance development while balancing performance, readability, and usability.
0 citationsRead paper