2026年9月8日 技术热点总结

项目简介：Turn the user’s description or uploaded reference into a finished, editable Blender card and an interactive Three.js page. Preserve the requested subject, style, typography and destination. This skill contains code and text only; generated artwork belongs in the user’s output project.

技术栈：Python

核心介绍：实现教程来源（补上，感谢大佬的教程）：小红书@乌托邦的香蕉🍌 > 一个 Codex Skill：对 Codex 说一句话，收获一张会随视角流光溢彩的 3D 全息闪卡。 > 能在浏览器里拖着转、翻到背面、拉滑块看它闪；还附赠一个可以随便改的 Blender 工程。 小时候在文具店门口舍不得买的那种闪卡，现在你想印谁就印谁。 你：「给我做一张赛博朋克风的机械猫闪卡，背景霓虹雨夜，编号 No.007」 🎨 画好四层图（主体 / 背景 / 线稿 / 文字） 🧊 搭好 Blender 场景，视差、镭射、星光一次到位 🌐 组装成 Three.js 网…

项目简介：Take a photo of real objects, and paste them in Blender

技术栈：JavaScript

核心介绍：Point your phone at an object, take a photo, and watch a 3D model appear in Blender in under a minute. Take photo → background removed → 3D model generated → auto-imported into Blender. The camera UI is built for phone. You run the server on the computer where Blender is open, then open the web app on your phone. A laptop webcam works too.

项目数据：⭐ 654 Stars，🍴 69 Forks

项目简介：基于 Cloudflare WARP / MASQUE 的可视化注册、配置生成与多客户端转换工具。 生成、Clash/Mihomo 智能分流、Shadowrocket、sing-box、本地 VLESS 桥接，以及可选的 WARP 出口检测。

技术栈：JavaScript

核心介绍：> 基于 Cloudflare WARP / MASQUE 的可视化注册、配置生成与多客户端转换工具。 > 支持 Cloudflare Pages + Cloudflare Workers 双部署，浏览器完成 Usque 注册、原生配置保存、MASQUE 多节点生成、Clash/Mihomo 智能分流、Shadowrocket、sing-box、本地 VLESS 桥接，以及可选的 WARP 出口检测。 > # YouTube视频教程 点击查看 > # v6.17 视频教程 点击查看 它解决的主要问题是： 手动注册 WARP / MASQUE 不同客户端格式不一致 需要手工写 Clash / sing-box / VLESS 配置 本项目把整个流程整理成： 一键注册 Usque / WARP MASQUE 自动下载原生 config.json 按需要设置 Endpoint / Port / SNI / DNS / 节点数量 一键生成客户端配置 Clash…

Benchmarks for the side effects an agent causes on the way to a goal already exist, but HarvestBench is the first to put a price on avoiding the side effect and to name that side effect as a living creature. It is a farm simulation: LLM sub-agents drive a crew of two tractors through a cooperative corn harvest, with animals in the field. The environment is a reinforcement learning gridworld, every decision is made without memory, and the harm is never named in the goal. When an animal blocks a tractor's route the autopilot stops and asks the model whether to drive on, at no fuel cost, or sw…

Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fragments across chat tools, IDEs, terminals, and writing environments, and the decisions that make it auditable are rarely preserved. We present Dr. Claw, an open-source workspace that wraps existing coding-agent executors in a controllable and auditable human-in-the-loop workflow rather than introducing another autonomous agent. Persistent state objects, a reusable skill library, and multi-executor coordination link human decisions to AI exec…

Vision-language models (VLMs) are expected to respond helpfully to appropriate requests while withholding compliance with requests that are incorrect, unsafe, infeasible, or unanswerable. However, existing benchmarks predominantly evaluate non-compliance at the level of the query as a whole, assuming that each request either warrants compliance or requires withholding compliance. In practice, real-world queries can contain a mixture of answerable content and components for which compliance should be withheld. In this paper, we introduce KoNA, a benchmark for evaluating selective non-complia…

Striking a balance between helpfulness and safety remains a fundamental challenge in aligning large language models. To achieve this balance, models should refuse harmful queries (e.g., "How do I shoot someone?") while remaining responsive to benign inputs, even those superficially resembling harmful queries (e.g., "Where can I shoot a good photo?"). However, models often struggle to distinguish genuinely harmful queries from benign queries that contain superficially risky language, resulting in false refusals. In this paper, we address the issue by decomposing a response in the safety-tuni…

The ambition of the 2025 PNPL competition (Landau et al., 2025) was to launch a multi-year curriculum for non-invasive speech decoding. Designed to progress from foundational tasks toward the linguistic complexity required for a practical brain-computer interface (BCI), it set the stage with speech detection and phoneme classification tasks. Winning submissions reached F1-macro scores of 95.6% and 73.6% on the respective tasks (Elvers et al., 2026), highly significant advances. This success was built on the LibriBrain dataset (Özdogan et al., 2025), the largest within-subject MEG dataset re…

Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are topology-constrained: they rely on category-specific templates or require per-skeleton fine-tuning and reference motions at inference. We present UniMate, a unified foundation model that synthesizes articulated motion for arbitrary skeletons from a rigged 3D asset and a text prompt, with no test-time optimization or per-skeleton retraining. UniMate introduces a topology-aware diffusion transformer, which integrates …