1
Leveraging Color Naming for Image Enhancement
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…
2
Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs
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…
3
PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training
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…
4
Loss-Conditional PINNs for Parametric PDE Families
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…
5
Parallax: Parameterized Local Linear Attention for Language Modeling
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…
6
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
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…
7
ParaTool: Shifting Tool Representations from Context to Parameters
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…
8
Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generation
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…
9
Strategic Over-Parameterization for Generalizable Low-Rank Adaptation
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…
10
Parameterized Hardness of Zonotope Containment and Neural Network Verification
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…
11
阿里 QoderWork 上线设计工作台：语音描述就能交付专业设计
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…