📄 arXiv 论文速递

💡 该论文解决了非耦合无遗憾动态中个体遗憾的对数依赖问题，首次实现常数遗憾，为分布式博弈达到均衡提供了更优的理论保证，对多智能体系统设计具有基础性意义。

Uncoupled no-regret dynamics provide a decentralized route to equilibrium, but prior guarantees for individual regret retain a polylogarithmic dependence on the horizon. We remove …

💡 该论文弥合了模型控制与学习策略在长时程操作中的分歧，提出持久化程序框架，实现语言引导的控制到学习再到真实部署的闭环，对机器人复杂任务泛化至关重要。

Bridging model-based control and learned policies in long-horizon manipulation has harbored a silent disagreement: control executes specified objectives, learning amortizes that be…

💡 该论文为仿射潜参数化神经网络提供了尖锐的逼近率刻画，填补了参数高效生成方法理论分析的空白，对理解低维表示与网络表达能力的关系具有重要理论价值。

Many parameter-efficient methods generate the parameters of a large neural network from a low-dimensional latent representation. Given an architecture $Φ$ with $P_Φ$ parameter slot…

💡 该论文针对2025-2026年AI市场匿名模型发布潮，提出四阶段黑盒身份验证协议，解决了匿名模型审计中的关键安全与信任问题，对监管和合规实践具有直接指导意义。

The 2025--2026 AI market has seen a wave of stealth releases: frontier models launched anonymously on developer platforms under codenames. For their users, identity determines data…

Ontology alignment (OA) has evolved through several methodological paradigms, ranging from lexical and structural aligners to knowledge graph embedding (KGE) models and, more recen…

Neural network mixed-effects models (NMMs) have gained traction by combining the strong representation and predictive power of artificial neural networks with the capacity of mixed…

The motivation for this paper is the investigation of the trade-offs implicit in probabilistic models used in machine learning. Models are often used to make predictions in the for…

💡 该论文通过受控实验系统研究LLM规模对本体学习性能的影响，首次明确规模效应的边界条件，为资源分配和模型选择提供实证依据，对知识工程领域具有实践价值。

The effect of Large Language Model (LLM) scale on ontology learning (OL) performance remains insufficiently characterized. We present a controlled evaluation of 13 models spanning …

Generative models have become central across science and industry, from image and text synthesis to the design of molecules and materials. Quantum generative models are considered …

Efficient evaluation changes the protocol used to support claims about model behavior, yet it is rarely tested whether those claims remain stable after the evaluation itself is mad…

Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of magnitude more interactions …

Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixture budgets without regressing …