提出一种自监督语义扩散方法，让技能像参数一样被训练与迁移，为AI技能学习开辟新思路。
arXiv:2607.27557v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable general instruction-following capabilities, …
提出一种参数化扩散桥的新方法，扩展生成模型的理论边界。
arXiv:2607.22719v1 Announce Type: new Abstract: Multiplicative Gamma noise is a signal-dependent degradation in coherent imaging; synthetic aperture r…
利用颜色命名规则，解决传统深度图像增强中可解释性差与参数化不足的两大痛点。
arXiv:2607.08185v1 Announce Type: new Abstract: Enhancing images to make them visually appealing is a persistent challenge in computer vision. Many de…
大模型化身CAD装配师，用求解器约束生成参数化B-Rep模型，让AI从“会聊天”进化到“会建模”。
arXiv:2606.31252v1 Announce Type: new Abstract: Large language models can write plausible CAD scripts, but reliable industrial CAD modeling requires m…
强化学习如何让大模型更高效地遍历参数化知识？这篇论文给出新方法。
arXiv:2511.05933v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is often credited with improving language model reasoning at the…
大模型知识有语言壁垒，如何挖掘隐藏事实？这篇跨语言探索研究给出新视角。
arXiv:2606.24579v1 Announce Type: new Abstract: Parametric knowledge in Large Language Models is not equally accessible across languages. As a result,…
揭秘大模型“记忆检索”瓶颈：参数化事实性缺失，究竟是模型没存住还是没找到？
arXiv:2602.14080v2 Announce Type: replace-cross Abstract: Standard factuality evaluations of LLMs treat all errors alike, obscuring whether failures a…
解耦混合专家模型新范式，突破参数化知识注入瓶颈，架构创新值得关注
arXiv:2606.14243v1 Announce Type: new Abstract: Knowledge injection aims to equip large language models (LLMs) with external, domain-specific, or time…
多项式预条件层PC Layer通过重塑权重矩阵奇异值谱，稳定大模型预训练过程，提升训练质量与收敛效率。
arXiv:2606.06470v1 Announce Type: cross Abstract: We propose a preconditioning (PC) layer, a weight parameterization via polynomial preconditioner tha…
引入损失条件机制优化PINNs训练，高效求解参数化偏微分方程族
arXiv:2606.04420v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) approximate solutions of ODEs and PDEs by minimising a weight…
提出参数化局部线性注意力机制，在语言建模中兼顾效率与性能，为Transformer改进提供新思路。
arXiv:2605.29157v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the co…
揭秘LoRA微调大模型时如何“记住”信息，提出参数化记忆定律，深入理论分析注意力机制。
arXiv:2605.30260v1 Announce Type: cross Abstract: Large Language Models (LLMs) must continuously learn and update knowledge to remain effective in dyn…
将工具表示从上下文迁移到模型参数，提升大模型工具调用的鲁棒性与效率
arXiv:2605.29561v1 Announce Type: new Abstract: Tool calling extends large language models (LLMs) by enabling grounded interaction with external execu…
首个评估大模型文本生成参数化CAD能力的基准，推动AI辅助设计发展
arXiv:2605.18430v1 Announce Type: new Abstract: Text-to-CAD generation aims to create parametric CAD models from natural language, enabling rapid prot…
策略性过参数化提升低秩适应泛化能力，为参数高效微调提供新理论。
arXiv:2605.16470v1 Announce Type: new Abstract: Adapting large language models (LLMs) to downstream tasks via full fine-tuning is increasingly impract…
从参数化复杂度角度揭示了ReLU神经网络验证的困难性，为理解其计算极限提供新视角
arXiv:2509.22849v2 Announce Type: replace-cross Abstract: Neural networks with ReLU activations are a widely used model in machine learning. It is thu…
语音描述需求即可生成可运行、可编辑的专业设计，实现设计即代码并一键交付至开发工具，让普通人也能高效产出。
IT之家 5 月 18 日消息，阿里云今日宣布，QoderWork 正式上线设计工作台（Design Desk），支持语音输入， 用户可直接通过语音描述需求、下达指令 ，即可在无限画布上获得可运行、可编辑、可交付的设计产物，普通人也能产出专业设计。 IT之家从官方介绍获悉，设计工作台是 QoderW…