发现ChatGPT类AI中温度升高反而降低熵的奇特现象，颠覆直觉的动力学研究。
arXiv:2608.00939v1 Announce Type: cross Abstract: Increasing the temperature of an ordinary many-state system increases access to a wider range of sta…
BixRouter 是一款非线性的 AI 聊天界面，让你同时与 OpenRouter 上的多个模型对话，自由切换分支探索不同思路。
Using chat interfaces often spawns many different thoughts, and while the AI and it's agents are okay at keeping track of it, I'm not always there. I …
非参数化Koopman算子在控制领域的突破，为非线性系统建模与控制提供全新视角
arXiv:2405.07312v5 Announce Type: replace-cross Abstract: This paper presents a novel Koopman composition operator representation framework for contro…
非线性状态空间模型遇上递归熵变分推断，新方法突破复杂概率推理难题。
arXiv:2511.15409v2 Announce Type: replace Abstract: We present a class of algorithms for state estimation in nonlinear, non-Gaussian state-space model…
揭秘LLM训练中学习率缩放的非线性规律，为优化大模型训练过程提供全新理论视角。
arXiv:2606.29158v1 Announce Type: new Abstract: Learning-rate transfer can reduce the cost of training large language models: instead of sweeping lear…
将机器学习与偏微分方程结合，用算子学习破解周期域上的三次非线性薛定谔方程，开启科学计算新范式。
arXiv:2606.27459v1 Announce Type: new Abstract: We consider the cubic nonlinear Schr\"odinger (NLS) equation on two-dimensional flat tori with varying…
利用系统的非线性特性，破解智能故障诊断中数据稀缺难题的创新方法。
arXiv:2606.20323v1 Announce Type: new Abstract: Deep Transfer Learning (DTL) allows for the efficient building of Intelligent Fault Diagnosis Systems …
用神经网络逼近非线性动力系统，并给出严格误差上界认证，让AI黑箱变透明。
arXiv:2505.15497v3 Announce Type: replace Abstract: Neural networks hold great potential to act as approximate models of nonlinear dynamical systems, …
ICML'26收录，首个工业级优化建模基准，为大规模整数与非线性规划研究提供标准化测试平台。
arXiv:2602.10450v2 Announce Type: replace-cross Abstract: Optimization modeling underpins decision-making in logistics, manufacturing, energy, and fin…
非线性变换防御不可学习数据集，对抗数据爬取，保护隐私的学术新方法
arXiv:2406.02883v2 Announce Type: replace Abstract: Automated scraping stands out as a common method for collecting data in deep learning models witho…
非线性贝叶斯滤波新突破：用分数匹配完成预测-更新循环，解决密度表示难题
arXiv:2605.16644v1 Announce Type: cross Abstract: A central obstacle in nonlinear Bayesian filtering is representing the belief distribution. Moment-b…
Koopman算子遇上小波变换，为非线性动力学分析提供新框架
arXiv:2605.14224v1 Announce Type: cross Abstract: We present an in-depth analysis of the Koopman semigroup via wavelet transform. Towards this goal, w…
数字孪生参数估计新方法：加权流匹配融合物理信息非线性滤波，提升推断精度
arXiv:2605.17146v1 Announce Type: cross Abstract: Digital twins (DTs) rely on continuous synchronization between physical systems and their virtual co…
用β-TCVAE模型从脑功能磁共振数据中分离非线性独立源，揭示大脑网络隐藏信号。
arXiv:2605.16708v1 Announce Type: new Abstract: Learning meaningful latent representations from nonlinear fMRI data remains a fundamental challenge in…
将摊销思想引入能量基贝叶斯推断，用传输方法一键解决非线性反问题，告别逐次MCMC的昂贵计算。
arXiv:2605.15407v1 Announce Type: cross Abstract: We consider amortized Bayesian inference for nonlinear inverse problems in settings where only sampl…
把线性LLM对话变成空间画布上的分支交互，解决备选探索和长对话管理难题。
arXiv:2605.15848v1 Announce Type: cross Abstract: Conversational interfaces powered by large language models (LLMs) are widely used for ideation and a…
用混沌动力学启发新判别器，对抗框架破解语音高频恢复难题
arXiv:2507.15970v3 Announce Type: replace-cross Abstract: Recovering high-frequency components lost to bandwidth constraints is crucial for applicatio…
突破线性干预局限，提出大模型非线性特征干预新方法，为理解LLM内部表征开辟新路径
arXiv:2605.14749v1 Announce Type: cross Abstract: Intervention is one of the most representative and widely used methods for understanding the interna…