Zobrazeno 1 - 10
of 113
pro vyhledávání: '"WU Haoze"'
Publikováno v:
口腔疾病防治, Vol 31, Iss 10, Pp 756-760 (2023)
Endodontic infection control is crucial to successful root canal treatment. Irrigation is the key step in endodontic procedures, and the application of root canal irrigation and disinfection medications play an important role. How to enhance antibact
Externí odkaz:
https://doaj.org/article/9d3092c3a1d145d2b6d90b2829e123c2
Building on VeriX (Verified eXplainability, arXiv:2212.01051), a system for producing optimal verified explanations for machine learning model outputs, we present VeriX+, which significantly improves both the size and the generation time of verified
Externí odkaz:
http://arxiv.org/abs/2409.03060
Autor:
Mandal, Udayan, Amir, Guy, Wu, Haoze, Daukantas, Ieva, Newell, Fletcher Lee, Ravaioli, Umberto, Meng, Baoluo, Durling, Michael, Hobbs, Kerianne, Ganai, Milan, Shim, Tobey, Katz, Guy, Barrett, Clark
In recent years, deep reinforcement learning (DRL) approaches have generated highly successful controllers for a myriad of complex domains. However, the opaque nature of these models limits their applicability in aerospace systems and safety-critical
Externí odkaz:
http://arxiv.org/abs/2407.07088
Mixture-of-Experts (MoE) has been demonstrated as an efficient method to scale up models. By dynamically and sparsely selecting activated experts, MoE can effectively reduce computational costs. Despite the success, we observe that many tokens in the
Externí odkaz:
http://arxiv.org/abs/2406.12375
Autor:
Mandal, Udayan, Amir, Guy, Wu, Haoze, Daukantas, Ieva, Newell, Fletcher Lee, Ravaioli, Umberto J., Meng, Baoluo, Durling, Michael, Ganai, Milan, Shim, Tobey, Katz, Guy, Barrett, Clark
Deep reinforcement learning (DRL) is a powerful machine learning paradigm for generating agents that control autonomous systems. However, the ``black box'' nature of DRL agents limits their deployment in real-world safety-critical applications. A pro
Externí odkaz:
http://arxiv.org/abs/2405.14058
Autor:
Wu, Haoze, Isac, Omri, Zeljić, Aleksandar, Tagomori, Teruhiro, Daggitt, Matthew, Kokke, Wen, Refaeli, Idan, Amir, Guy, Julian, Kyle, Bassan, Shahaf, Huang, Pei, Lahav, Ori, Wu, Min, Zhang, Min, Komendantskaya, Ekaterina, Katz, Guy, Barrett, Clark
This paper serves as a comprehensive system description of version 2.0 of the Marabou framework for formal analysis of neural networks. We discuss the tool's architectural design and highlight the major features and components introduced since its in
Externí odkaz:
http://arxiv.org/abs/2401.14461
Quantization replaces floating point arithmetic with integer arithmetic in deep neural network models, providing more efficient on-device inference with less power and memory. In this work, we propose a framework for formally verifying properties of
Externí odkaz:
http://arxiv.org/abs/2312.12679
Correctness of results from mixed-integer linear programming (MILP) solvers is critical, particularly in the context of applications such as hardware verification, compiler optimization, or machine-assisted theorem proving. To this end, VIPR 1.0 is t
Externí odkaz:
http://arxiv.org/abs/2312.10420
The demonstrated code-understanding capability of LLMs raises the question of whether they can be used for automated program verification, a task that demands high-level abstract reasoning about program properties that is challenging for verification
Externí odkaz:
http://arxiv.org/abs/2310.04870
Autor:
Wu, Haoze, Hahn, Christopher, Lonsing, Florian, Mann, Makai, Ramanujan, Raghuram, Barrett, Clark
We present Self-Driven Strategy Learning ($\textit{sdsl}$), a lightweight online learning methodology for automated reasoning tasks that involve solving a set of related problems. $\textit{sdsl}$ does not require offline training, but instead automat
Externí odkaz:
http://arxiv.org/abs/2305.11087