将带噪梯度下降理想化为过阻尼朗之万动力学，量化模型参数落入危险区域的概率，为训练安全提供理论保证。
arXiv:2607.07538v1 Announce Type: new Abstract: Training a model with noisy gradient descent can be idealized as overdamped Langevin dynamics on the l…
用贝叶斯教师指导SGD蒸馏，理论框架与实用指南双管齐下，读懂知识蒸馏新范式。
arXiv:2601.01484v2 Announce Type: replace Abstract: Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher …
用微分同胚映射优化高维流形，破解非凸损失下的生成模型训练难题，让梯度下降目标更清晰。
arXiv:2607.00947v1 Announce Type: new Abstract: Generative models learn data distributions that reside on a low-dimensional manifold within a higher-d…
不做梯度更新也能学习？这篇论文揭示了上下文学习背后的隐式动力学机制
arXiv:2507.16003v4 Announce Type: replace Abstract: One of the most striking features of Large Language Models (LLMs) is their ability to learn in-con…
像梯度下降优化参数一样优化AI代理技能，全新SkillGrad方法带来更高效的自适应学习范式。
arXiv:2605.27760v1 Announce Type: new Abstract: Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable …
OpenAI提出简单高效的元学习算法Reptile，通过重复采样任务和SGD更新，实现快速适应新任务
We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on i…
高维视角下SGD在对角线性网络中的极限行为，理论深度与前沿性兼备
arXiv:2605.17177v1 Announce Type: cross Abstract: Understanding the behavior of stochastic gradient methods is a central problem in modern machine lea…