毫米波技术赋能人体测量，非接触高精度成像新方案，arXiv最新研究突破。
arXiv:2605.23064v1 Announce Type: cross Abstract: Body shape and circumferences are clinically informative biomarkers for risk stratification, includi…
首次探索如何利用基础模型推动因果生成建模，为新范式研究提供理论基石。
arXiv:2605.23861v1 Announce Type: cross Abstract: Causal generative modeling is essential for developing reliable and transparent AI systems capable o…
从零基础到AI研究员的8阶段系统学习路线，完整覆盖LLM核心理论与实践前沿。
Article URL: https://github.com/barvhaim/llm-learning-path Comments URL: https://news.ycombinator.com/item?id=48255624 Points: 1 # Comments: 0
提出Token级LLM协作新方法FusionRoute，突破领域模型融合粒度，让小模型协同超越大模型。
arXiv:2601.05106v4 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strengths across diverse domains. However, achieving st…
提出运动补偿框架，有效抑制头部运动伪影，大幅提升3D脑部MRI重建清晰度
arXiv:2605.22121v1 Announce Type: new Abstract: Magnetic resonance imaging (MRI) is highly susceptible to patient motion due to its relatively long ac…
视频人体重打光迎来新突破，时间一致性让全身光影流转更加自然
arXiv:2605.21766v1 Announce Type: new Abstract: Being able to relight human performance is a fundamental task for post production and content creation…
顶级会议ICML 2026收录，揭秘构建强视觉-语言-动作（VLA）模型的实用配方与技巧。
arXiv:2602.18532v2 Announce Type: replace Abstract: Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, lever…
打破多模态数据对齐瓶颈，论文提出仅用成对模态训练MLLM，显著提升跨域可扩展性。
arXiv:2605.21059v1 Announce Type: cross Abstract: Despite the impressive results achieved by multimodal large language models (MLLMs), their training …
场景文本编辑新框架TextSculptor，训练与基准测试双突破，AI文字处理再升级。
arXiv:2605.21090v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have…
突破性研究：首次实现无限深和宽Transformer的可训练性，彻底解决深层网络训练瓶颈
arXiv:2605.17660v1 Announce Type: cross Abstract: Transformers have become the dominant architecture in modern machine learning, yet the theoretical u…
突破传统MMSE，用ProxiMAP提升PnP图像恢复性能，理论创新与实验验证兼具。
arXiv:2605.16396v1 Announce Type: cross Abstract: Plug-and-Play (PnP) methods have become standard tools for solving imaging inverse problems by repla…
揭秘SGD在LLM预训练中不如Adam的根源：大有效学习率的关键作用。
arXiv:2605.17787v1 Announce Type: new Abstract: It is widely believed that stochastic gradient descent (SGD) performs significantly worse than adaptiv…
结合层代数与神经ODE，实现高保真脑动力学生成，为脑科学计算建模开辟新路径。
arXiv:2605.19324v1 Announce Type: new Abstract: Efficient neural network models that generate brain-like dynamic activity can be a valuable resource f…
视觉-only BEV感知新框架Fast-BEV++，在精度与部署效率间找到平衡，加速自动驾驶落地。
arXiv:2512.08237v3 Announce Type: replace Abstract: The advancement of vision-only Bird's-Eye-View (BEV) perception, a core paradigm for cost-effectiv…
提出DISK可微稀疏核复合体，实现高效空间可变卷积，已被ICLR 2026接收。
arXiv:2512.04556v2 Announce Type: replace-cross Abstract: Image convolution with complex kernels is a fundamental operation in photography, scientific…
MoE架构在严格等资源条件下首次证明超越稠密大模型，ICLR 2026最新研究。
arXiv:2506.12119v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) language models dramatically expand model capacity and achieve remarkable…
如何自动将神经网络实现从一种深度学习框架迁移到另一种？这篇论文提出新方法，解决框架间兼容性难题
arXiv:2511.02610v2 Announce Type: replace Abstract: The development of smart systems (i.e., systems enhanced with AI components) has thrived thanks to…
IJCAI 2026 接收，利用内在光照先验突破低光图像增强，效果显著。
arXiv:2605.19982v1 Announce Type: new Abstract: Low-Light Image Enhancement (LLIE) has long been a challenging problem in low-level vision, as insuffi…
提出DarkLLM框架，利用大语言模型自动生成语言驱动的对抗样本，攻破NLP模型防线
arXiv:2605.18868v1 Announce Type: cross Abstract: While vision and multimodal foundation models underpin critical tasks from perception to complex rea…
线性注意力机制迎来精确化突破，三大工程创新解决梯度退化与特征流动难题
arXiv:2605.18848v1 Announce Type: new Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational com…