📅 今天是2026年11月16日,以下是今日技术热点深度总结,涵盖GitHub最新热门开源项目及AI前沿研究成果。
🔥 GitHub 热门开源项目详解
以下为近7天内新建或迅速爆火的开源项目(数据来源:GitHub Trending):
🔤 JavaScript | 🍴 156 Forks | 🌐 官网
项目简介:A dreamy underwater world you can swim through in your browser: swaying kelp forests, sunbeams, a sunken ship and manta rays. Everything is generated by code with WebGPU (no images, models or sound files), all in a single 97 KB HTML file.
技术栈:JavaScript
核心介绍:Towering kelp forests, sunbeams pouring through a rippling surface, a sunken ship, manta rays gliding overhead. And all of it is made by code: no images, no 3D models, no sound files. The whole world fits in one 96 KB HTML file. 1. Download index.html. 2. Open it in Chrome or Edge on a desktop computer. 3….
🔤 – | 🏷️ ai-agents, ai-assistant, blender, blender-addon, blender-ai | 🍴 29 Forks
项目简介:AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with ChatGPT/GPT, Claude, Gemini, Ollama, OpenCode. Blender AI addon, copilot for 3D, bpy Python scripting, MCP integration.
技术栈:ai-agents、ai-assistant、blender、blender-addon、blender-ai、blender-automation、blender-mcp、blender-plugin
核心介绍:Download · Getting started · Connections and agents Start with an idea. Ask the assistant to inspect your scene, create a product-display layout, arrange objects, assign materials or prepare an export. Follow its actions in the conversation and i…
🔤 Python | 🍴 445 Forks
项目简介:muse.ai 注册与邀请码兑换协议研究(纯 HTTP Python 实现)
技术栈:Python
核心介绍:补充一下,记得用JP 节点, JP 不需要绑卡,直接过 纯 HTTP 实现 muse.ai 的注册与邀请码兑换流程,不依赖浏览器。本文记录的是通过抓包逐字段比对得出的协议细节。 pip install -r requirements.txt cp config.example.json config.json # 填入邮箱与可选代理 python example_register.py client.py 注册 + 兑换的完整协议客户端 runner.py 多账号批量调度(sticky 代理 / 预算 / 停止语义) otp.py 验证码轮询(幂等:只取 send 之后的最新码) falco.py 行为埋点上报(可选) caa.py 注册漏斗事件上报(可选) example_register.py 单账号端到端示例 example_batch.py 多账号批量示例 config.example.json 配置模板
项目数据:⭐ 1,011 Stars,🍴 445 Forks
🔤 Kotlin | 🍴 87 Forks
项目简介:基于 Shizuku 免 Root 清除国产安卓 SystemHelper、RegService 等系统预装隐私数据收集模块
技术栈:Kotlin
核心介绍:> 运营商为终端入网、自注册、网络运维和故障排查,确有在相应场景收集必要数据的实际需求!本项目仅供学习,用于了解 Android 系统包管理机制。 TelemetryCleaner 可以检测国行 Android 固件预置的运营商组件,查看各空间的安装状态和权限,并管理卸载与恢复。下载: GitHub Releases 您可通过不限于以下方式参与贡献,欢迎 PR: 1. 提供清单未覆盖的厂商+运营商+包名线索,在 README.md 中补充即可; 2. 提供针对某模块的实测与分析报告,不限制是否为 AI 生成,但需保证真实性。放于 docs 目录中即可; 3. 协助实现未支持的免 Root 卸载功能(如现版本不支持部分 vivo 系的电信/移动组件卸载); 4. 对软件功能的反馈或改进。 部分国产厂商在国行固件中预置了 SystemHelper、RegService 等运营商终端管理组件。这些组件在后台静默定时采集数据,用户无感;没有桌面入口,同时无法以常规手段禁用权限和卸载。
项目数据:⭐ 992 Stars,🍴 87 Forks
🤗 HuggingFace 热门论文深度解读
以下为HuggingFace Daily Papers中今日关注度最高的AI论文:
Self-evolving agents improve their own skills, memory, and harness code from experience without retraining the base LLM, and group-evolving agents go further by sharing these lessons across agents. Yet most such systems overlook that sharing across users and heterogeneous agents requires deciding who can benefit from each lesson and what information must remain private. We present MixUA, a memory system that distills independent user-agent trajectories into lessons and assigns each lesson to a user-agent pair, user, agent, or global scope according to whom it benefits and what it may disclo…
Generalist manipulation policies can benefit from the complementary experience of humans, real robots, and simulated agents. However, differences in morphology, sensing, and control interfaces make it difficult to learn effectively from their combined demonstrations. We introduce EgoX, an egocentric cross-embodiment learning framework that organizes heterogeneous demonstrations through semantically corresponding observation and action modalities. EgoX pretrains a Modularized Cross-Embodiment Transformer with Embodiment Dreaming (MXT+) on this mixture and fine-tunes it on target-embodiment d…
Frontier video generation models work in a VAE latent space that compresses video in both space and time. This compression made training tractable, but now limits high-resolution, controllable, and interactive generation — doubling resolution quadruples token count, conditions apply to groups of frames rather than individual ones, and each response must wait for the rest of its multi-frame block. We present PixVid, a simple yet effective method that lifts a pretrained latent video model to directly generate every frame in pixel space. PixVid keeps the diffusion transformer and replaces the…
Reference-frame stabilization registers every frame of a hovering-drone video onto one reference frame, keeping object positions comparable. The registration pipelines it relies on are selected on feature-matching benchmarks in which only the camera moves. Over a busy intersection, vehicles moving together supply mutually consistent correspondences that can draw the robust homography estimate toward their motion: consensus capture, which inlier statistics cannot flag. A two-part benchmark measures it and the object masking meant to prevent it. A static protocol scores ten pipelines under ex…
Machine-learning surrogates are increasingly used to accelerate computational fluid dynamics, yet progress is limited by the lack of benchmarks capturing realistic, time-dependent turbulent flows. We introduce TurtLES, a 14 TB dataset of 3D turbulent cylinder wakes in the shear-layer transition regime, computed via high-fidelity implicit large-eddy simulations. The dataset contains 400 trajectories of 400 time steps each, with 3-11 million points per frame, spanning variations in geometry, Reynolds number, and angle of attack. Unlike existing datasets, TurtLES combines (i) physically realis…
Existing adaptive-reasoning methods shorten the explicit reasoning a model writes, or skip it by switching modes; either way the answer is still written out token by token. Rather than deciding how much to think, we explore a different paradigm, zero-or-T thinking: a single model either answers from the implicit thinking inside one forward pass, generating no token, or performs full autoregressive reasoning at a cost of T tokens when that is worth paying. We realise it in a hybrid decision model (HDM), where one frozen backbone serves both modes and a lightweight self-routing block chooses …
📌 今日小结
以上为2026年11月16日的技术热点深度总结。共收录 4 个GitHub热门开源项目和 6 篇AI前沿论文。
从本周趋势来看,JavaScript 是本期的热门编程语言,AI Agent、大模型应用、开发工具等方向持续受到开发者关注。保持学习,紧跟前沿!
更多精彩内容请持续关注 汤不热吧。
本文由系统自动生成于2026年11月16日,数据来源:GitHub API、HuggingFace Daily Papers
相关