MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models
研究解决了工具增强型大语言模型在工具返回与参数记忆冲突时的仲裁问题,通过引入MemToC基准进行评估,并采用SFT和DPO方法改进了正确答案保留率。
研究解决了工具增强型大语言模型在工具返回与参数记忆冲突时的仲裁问题,通过引入MemToC基准进行评估,并采用SFT和DPO方法改进了正确答案保留率。
本文通过构建Solana数字资产时间序列数据集,结合多种变量分析了市场结构,并使用PatchTST等模型进行了预测,揭示了影响代币波动性的生态系统因素。
This study investigates whether a directed graph admits an edge labeling over a finite alphabet that renders it a completely reachable automaton, and characterizes those graphs—termed fully labeling-robust—for which every possible labeling yields complete reachability. By integrating tools from graph theory, automata theory, and computational complexity, the work provides the first complete structural characterization of directed graphs that can realize completely reachable automata. The main contributions include a polynomial-time algorithm for recognizing such graphs, a proof that the decision problem is NP-complete when the alphabet size is fixed, and a full classification of fully labeling-robust graphs.
This work addresses the vulnerability of traditional image encryption schemes that rely on fixed S-boxes lacking input dependency, rendering them susceptible to linear and differential cryptanalysis. To overcome this limitation, the authors propose a novel hybrid approach integrating convolutional neural networks (CNNs) with classical cryptographic principles. Specifically, a pre-trained CNN extracts salient features from the input image to dynamically generate a personalized S-box for pixel substitution. This method represents the first implementation of content-adaptive S-box generation driven by the plaintext image itself, substantially enhancing the nonlinearity, uniqueness, and resilience of the encryption process against statistical and structural attacks. Experimental results demonstrate superior performance over conventional techniques across multiple security metrics, including information entropy, histogram uniformity, pixel correlation, NPCR, and UACI, thereby achieving both heightened security and greater flexibility.
This work proposes a novel image encryption framework that integrates fractal geometry with Fourier transform, addressing the longstanding challenge of simultaneously achieving high security, image fidelity, and computational efficiency in traditional methods. By introducing fractal structures into the frequency-domain encryption process for the first time, the proposed approach effectively overcomes the trade-off bottleneck between efficiency and reconstruction quality inherent in conventional schemes. Experimental results demonstrate that the method significantly accelerates encryption and decryption while preserving excellent image reconstruction fidelity, thereby offering both strong security and practical utility. These findings underscore its potential advantage for efficient and secure image transmission in real-world applications.
研究解决了工具增强型大语言模型在工具返回与参数记忆冲突时的仲裁问题,通过引入MemToC基准进行评估,并采用SFT和DPO方法改进了正确答案保留率。
本文通过构建Solana数字资产时间序列数据集,结合多种变量分析了市场结构,并使用PatchTST等模型进行了预测,揭示了影响代币波动性的生态系统因素。
This study investigates whether a directed graph admits an edge labeling over a finite alphabet that renders it a completely reachable automaton, and characterizes those graphs—termed fully labeling-robust—for which every possible labeling yields complete reachability. By integrating tools from graph theory, automata theory, and computational complexity, the work provides the first complete structural characterization of directed graphs that can realize completely reachable automata. The main contributions include a polynomial-time algorithm for recognizing such graphs, a proof that the decision problem is NP-complete when the alphabet size is fixed, and a full classification of fully labeling-robust graphs.
This work addresses the vulnerability of traditional image encryption schemes that rely on fixed S-boxes lacking input dependency, rendering them susceptible to linear and differential cryptanalysis. To overcome this limitation, the authors propose a novel hybrid approach integrating convolutional neural networks (CNNs) with classical cryptographic principles. Specifically, a pre-trained CNN extracts salient features from the input image to dynamically generate a personalized S-box for pixel substitution. This method represents the first implementation of content-adaptive S-box generation driven by the plaintext image itself, substantially enhancing the nonlinearity, uniqueness, and resilience of the encryption process against statistical and structural attacks. Experimental results demonstrate superior performance over conventional techniques across multiple security metrics, including information entropy, histogram uniformity, pixel correlation, NPCR, and UACI, thereby achieving both heightened security and greater flexibility.
This work proposes a novel image encryption framework that integrates fractal geometry with Fourier transform, addressing the longstanding challenge of simultaneously achieving high security, image fidelity, and computational efficiency in traditional methods. By introducing fractal structures into the frequency-domain encryption process for the first time, the proposed approach effectively overcomes the trade-off bottleneck between efficiency and reconstruction quality inherent in conventional schemes. Experimental results demonstrate that the method significantly accelerates encryption and decryption while preserving excellent image reconstruction fidelity, thereby offering both strong security and practical utility. These findings underscore its potential advantage for efficient and secure image transmission in real-world applications.