2026年11月8日 技术热点总结

项目简介：A Native Recompilation Of The Legend Of Zelda: Ocarina Of Time Nintendo Switch 2 Remake

技术栈：C++

项目数据：⭐ 1,794 Stars，🍴 159 Forks

技术栈：JavaScript

核心介绍：> 用途说明： 本项目仅以教学与研究为目的提供。使用真实平台前应取得必要授权，遵守适用法律和平台条款；不得伪造身份、学籍或材料，不得冒用信息、骗取权益或绕过资格审核。本项目与 SheerID 及任何学校均无官方隶属或认可关系，也不保证验证成功。详情见 用途说明与免责声明，代码许可见 ISC 协议。 需要 Node.js >= 22.15 与 npm。从 GitHub 获取源码： git clone https://github.com/JenkinWoo/sheeridVerify.git 使用下载的 ZIP 时，解压后进入其中包含 package.json 的目录。在项目根目录安装依赖与浏览器： 首次使用时复制配置，已有个人配置请直接编辑原文件。 Windows PowerShell： Copy-Item config/sheerid.example.json config/sheerid.local.json cp -n config/sheerid.example.json config/sheerid.local.json

关键特性：通过 fetch 读取验证状态，按当前步骤选择浏览器或材料处理流程。；在 Web 页面创建、排队、停止、恢复和删除任务；失败任务删除后可重新提交。；按配置…

项目简介：3D modeling in Python, built for LLMs.

技术栈：HTML、3d、blender、cad、llm、procedural-modeling、python、usd

核心介绍：sand3d is a Python library for writing 3D objects as short programs: profiles, solids, edits, frames, joints and assemblies, over Blender’s bpy. A program says *how* a shape is made, part by part and in its own words, so a model writes it in a few hundred tokens and a person can read it. Website · Docs · Datasets ·

项目数据：⭐ 1,048 Stars，🍴 117 Forks

项目简介：Headless 3D and VFX engine for agents. Research preview.

技术栈：Rust、3d、ai-agents、gpu、metal、ray-tracing、rendering、rust、slang

核心介绍：vork, the Voyager rendering kernel, is a headless 3D and VFX engine built for agents. Watch the film: a car drives into the night as the forest turns into glowing cyan wireframe, drawn from real triangle edges by a scene shader. Credit: “Car Concept” by Unity Fan, glTF adaptation by Eric Chadwick / Darmstadt Graphics Group, CC BY 4.0. Changes: scaled, animated, brighter head and tail lights, wheel pose. Trees, ground and asphalt from Poly Haven

*…

项目简介：StudyOnTV (Tiledaoti TV) — open-source Android TV app where kids unlock screen time by answering questions. Runs fully on the TV: no server, no account. Parents scan a QR code and manage questions from the LAN. Learn first. Watch later.

技术栈：Kotlin、android、android-tv、children、digital-wellbeing、edtech、education、family、kids

项目数据：⭐ 837 Stars，🍴 199 Forks

Large language model (LLM) agents typically append raw tool outputs to their context. Over multi-step interactions, long and noisy observations incur substantial context overhead and dilute the agent's attention to task-relevant information. Existing token pruning and summarization methods remain constrained by discrete text representations, limiting the achievable compression ratios.
In this work, we challenge the prevailing assumption that agents must consume tool observations as explicit text tokens. To this end, we propose Coca-Cola, a continuous latent context compression model for L…

Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vectors. A signature proves who published a pack, not that its vectors encode its text. We study this text-vector integrity gap. A verifier that recomputes vectors and accepts them within a cosine tolerance concedes a predictable share of queries to an attacker who controls the vectors: the hijack rate equals the distribution of angular retrieval margins at the tolerance (the margin law). Margins are small in five corpora and two embedding models, …

A deployable text-to-image diffusion model must hold several capabilities at once, such as instruction following, text rendering and human preference, and must sample in a few steps. Capabilities and few-step sampling are built in separate stages: a full-step model first consolidates capabilities through multi-teacher on-policy distillation, then serves as a fixed teacher for step distillation. Every full-step model we evaluate scores lower once compressed, and the second stage cannot begin until the first finishes. We introduce StepX-OPD, which merges the two stages: one student acquires e…

LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation many times to maintain population diversity. We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decoding to text, and share information by passing KV caches. Each swarm studies the problem from a di…

Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them on research-level problems remains challenging. We introduce OpenFrontiers, a cross-disciplinary resource that combines a structured corpus of open research problems with a retrospective benchmark of recently resolved problems in mathematics. The corpus records problem statements, context, progress, and other information for 12,151 problems. The benchmark contains 200 problems, 110 resolved in 2026 and 90 still op…

Mathematical modeling turns an open-ended real-world problem into assumptions, a model, a solution, and a defended recommendation, and its answers matter only if they are both close to a credible reference and physically feasible; existing benchmarks either score solver fragments or grade reports with an LLM judge, leaving those numbers unchecked. We introduce TB-MathModel (the Terminal-style Mathematical Modeling Bench), the first benchmark to make complete contest-style modeling problems agentic, verifiable, and terminal at once, over 18 real CUMCM and MCM problems (2023–2025). Each task…