多视角射频感知融合，实现语义体素标注与三维目标检测，为各向异性成像难题提供新思路。
arXiv:2608.23249v1 Announce Type: new Abstract: We consider a multistatic radio-frequency imaging problem with anisotropy, in which the reflection fro…
从数学底层重新定义大语言模型，为理解LLM提供严谨的理论框架。
arXiv:2601.22170v2 Announce Type: replace-cross Abstract: Large language models (LLMs) process and predict sequences containing text to answer questio…
从DSA影像跨视角时空建模自动评估侧支循环，为脑血管病诊疗提供精准AI新方案。
arXiv:2608.18986v1 Announce Type: new Abstract: Digital subtraction angiography (DSA) is the reference standard for leptomeningeal collateral (LMC) as…
提出知识感知主动学习框架，精准提升大模型领域知识的掌握深度，为微调注入新思路。
arXiv:2603.17566v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) with high-quality knowledge has been shown to enhance the…
拆解Adam优化器背后的脆弱根基，用原理推导新设计，深度学习调参必备的理论参考。
arXiv:2608.16760v1 Announce Type: new Abstract: Reliable optimization is central to neural network (NN) training, yet Adam, the default optimizer for …
多视角眼底图像结合新型视觉Transformer，为卒中快速筛查提供高精度AI方案
arXiv:2608.14722v1 Announce Type: new Abstract: Stroke remains a leading cause of mortality and morbidity worldwide, emphasizing the importance of its…
深度学习中模型学到的是真实生物信号还是伪影？ICML 2026 论文以生物成像为例，拷问表征学习的本质，值得每一位科研工作者反思。
arXiv:2603.13377v2 Announce Type: replace-cross Abstract: Representation learning has driven major advances in natural image analysis by enabling mode…
用分布视角重新拆解知识蒸馏，带你理解模型压缩背后的数学本质，适合深度学习进阶读者。
arXiv:2608.15215v1 Announce Type: cross Abstract: Token-level knowledge distillation (KD) matches two conditional distributions per position, yet the …
AI视频生成新贵，获高盛英特尔4亿美元融资，创意视频制作更智能高效。
IT之家 8 月 17 日消息，据英国《金融时报》报道，AI 视频生成平台 Higgsfield 已从 DST Global、高盛、Liberty Global 和英特尔等投资者手中筹集 4 亿美元 （IT之家注：现汇率约合 26.99 亿元人民币） ，公司估值达到 54 亿美元 （现汇率约合 36…
随机权重平均遇上数据增强，简单组合就能显著提升模型泛化，炼丹必备技巧。
arXiv:2608.14373v1 Announce Type: new Abstract: The symmetries of a learning task have become an important factor in designing modern deep learning so…
理论剖析Transformer表达能力的边界，揭示大模型底层机制，值得算法研究者细读。
arXiv:2608.12671v1 Announce Type: new Abstract: Multi-layer transformers form the critical component of essentially all large language models (LLMs) i…
从零训练三个大语言模型，并放上线供你亲自试玩，体验AI训练成果。
Article URL: https://huggingface.co/spaces/JohnEnev/modern-llm-playground Comments URL: https://news.ycombinator.com/item?id=49299726 Points: 2 # Comm…
用车辆轨迹引导视频嵌入学习，一举提升驾驶视频检索精度。
arXiv:2608.13495v1 Announce Type: cross Abstract: Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, …
跨越数字与拍摄场景的OCR解析新框架，攻克透视畸变和复杂排版难题，自动化文档处理更精准。
arXiv:2608.12898v1 Announce Type: new Abstract: Document parsing aims to transform unstructured documents into structured and machine-readable represe…
城市级LiDAR点云变化检测新方案，助力高精度三维城市动态监测
arXiv:2510.21112v3 Announce Type: replace-cross Abstract: High-definition 3D city maps enable city planning and change detection, which is essential f…
热成像+深度学习实时预测网络硬件故障，为数据中心运维提供全新预警思路。
arXiv:2608.07582v1 Announce Type: new Abstract: Unplanned network hardware malfunctions can interrupt services and result in expensive downtime in dat…
面向脑部MRI的可持续扩展基础模型，探索动态架构与终身学习，为医学影像AI提供新范式。
arXiv:2608.08319v1 Announce Type: cross Abstract: Brain magnetic resonance imaging (MRI) is central to neuroscience and clinical assessment, but model…
全新模块化更新解耦机制，让大模型训练内存更省、并发更强，值得关注的前沿方案。
arXiv:2608.07974v1 Announce Type: new Abstract: Large language model (LLM) fine-tuning at the edge adapts the model to scenario-specific data while pr…
探究表征方式如何影响长期情感建模的可靠性，为纵向情感计算提供关键洞见。
arXiv:2608.07518v1 Announce Type: cross Abstract: Longitudinal, in-the-wild, wearable sensing yields day-level physiology, sleep, activity, and enviro…
用隐式神经表示给散斑噪声做“大扫除”，9页9图带你解锁高精度去噪新姿势。
arXiv:2608.06574v1 Announce Type: cross Abstract: Speckle fundamentally limits coherent imaging by introducing multiplicative, spatially correlated no…