在小型芯片上部署AI模型，Edge Impulse让你从云端到边缘一步到位，专为低功耗设备优化。
Article URL: https://www.easelinktech.com/why-every-electronic-product-may-need-to-be-rebuilt-for-on-device-ai-the-chip-layer-will-decide-the-next-har…
GitHub开源项目，让LLM应用拥有长期记忆，同时将输入token平均削减68%，大幅降低API成本。
Article URL: https://github.com/Tem-Degu/streetai-memory Comments URL: https://news.ycombinator.com/item?id=48249509 Points: 1 # Comments: 0
开源AI代理图语义记忆项目，整合SQLite、llama.cpp、BGE-M3等，30秒可安装体验。
Article URL: https://github.com/AEndrix03/Graft Comments URL: https://news.ycombinator.com/item?id=48216282 Points: 4 # Comments: 0
OpenAI对比预训练方法，学习文本与代码的高质量嵌入表示
多语言文本嵌入新方案ML-Embed，突破成本、语种和透明壁垒，迈向包容高效未来。
arXiv:2605.15081v1 Announce Type: cross Abstract: The development of high-quality text embeddings is increasingly drifting toward an exclusionary futu…
用认知嵌入高效筛选评估子集，大幅降低大模型评测成本，保持预测准确性。
arXiv:2510.26384v2 Announce Type: replace-cross Abstract: The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks …
提出连续域降维新范式，用神经算子嵌入离散点云，突破传统方法瓶颈
arXiv:2605.11970v2 Announce Type: replace Abstract: Most dimensionality reduction methods treat data as discrete point clouds, ignoring the continuous…
在图的分数傅里叶变换域中嵌入，突破传统谱嵌入的表达瓶颈，捕获更全面的图结构特征
arXiv:2508.02383v2 Announce Type: replace Abstract: Spectral graph embedding plays a critical role in graph representation learning by generating low-…
揭示坐标异质性如何主导二值量化，从InfoNCE损失到召回率的理论桥接，为高效嵌入压缩提供新洞察。
arXiv:2605.17524v1 Announce Type: new Abstract: Binary quantization (BQ) compresses high-dimensional embeddings into one or two bits per coordinate, e…
针对RAG系统数据泄露，提出隐私政策执行（PPE）框架，用双密度估计器与嵌入融合检测非规则属性聚类。
arXiv:2605.17034v1 Announce Type: new Abstract: Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribut…
发现CLIP模型嵌入空间存在164个噪声维度，协方差特征谱揭示视觉语言模型的结构异常
arXiv:2605.14893v1 Announce Type: cross Abstract: Contrastively pre-trained Vision-Language Models (VLMs) serve as powerful feature extractors. Yet, t…
本论文提出MATE方法，通过记忆累积转移嵌入解决上下文MDP中的长期依赖问题，为强化学习领域贡献新思路。
arXiv:2605.17431v1 Announce Type: new Abstract: We propose MATE, a simple yet effective memory architecture for solving Contextual Markov Decision Pro…
残差语义分解（RSD）新方法，用神经加性分解平衡词嵌入重建，值得关注。
arXiv:2605.17482v1 Announce Type: cross Abstract: We introduce Residual Semantic Decomposition (RSD), a neural additive decomposition of word embeddin…
OpenAI 推出文本与代码嵌入新端点，轻松实现语义搜索、聚类等高级 NLP 任务。
We are introducing embeddings, a new endpoint in the OpenAI API that makes it easy to perform natural language and code tasks like semantic search, cl…
基于扩散模型的文本生成新方法，通过在token嵌入上平滑去噪，实现高质量离散文本生成
arXiv:2505.18853v2 Announce Type: replace Abstract: Diffusion models have achieved state-of-the-art performance in generating images, audio, and video…
首次提出确定性Lp子空间核心集的迭代算法，覆盖任意p∈[1,∞)的ε-子空间嵌入
arXiv:2601.00361v3 Announce Type: replace-cross Abstract: We introduce the first iterative algorithm for constructing a $\varepsilon$-coreset that gua…
用词嵌入技术实现领域无关的博弈抽象，大幅提升复杂游戏策略的可迁移性
arXiv:2605.15543v1 Announce Type: cross Abstract: Many games of interest in the real world are often intractably large, thereby necessitating the use …
在iPadOS上运行桌面级AI终端，通过嵌入LinuxKit打破iOS限制，实验性但思路新颖。
Article URL: https://github.com/rcarmo/ios-terax-ai Comments URL: https://news.ycombinator.com/item?id=48173169 Points: 1 # Comments: 0
SpeakerLLM 将说话人理解与验证推理整合到自然语言界面，不仅区分‘是谁’，还能解释声音轮廓、录音条件等证据，为可解释的说话人认知铺平道路——这比单纯打分有用得多。
arXiv:2605.15044v1 Announce Type: cross Abstract: As audio-first agents become increasingly common in physical AI, conversational robots, and screenle…
一篇教你用8位微控制器（AVR芯片）搭建迷你Web服务器的硬核动手指南，代码与硬件全公开，极客味十足
Article URL: https://maurycyz.com/projects/mcusite/ Comments URL: https://news.ycombinator.com/item?id=48165295 Points: 211 # Comments: 17