53 个 · 按相关度排序
Turn a research proposal into an experiment plan tied to specific paper claims. Define comparisons, evaluation measures, tests that remove individual components, run order, and compute estimates, with a written plan and tracker for execution.
中文简介正在准备中。当前显示英语简介。
Evaluate language models on knowledge, math, coding, safety, and image understanding benchmarks. The skill guides reproducible runs in containers using local Docker, Slurm clusters, or cloud execution, with shared configurations for model comparison and result export.
中文简介正在准备中。当前显示英语简介。
Guides CDF Auto-Labeling workflows for annotating data such as videos. Routes tasks to specialized references, covering shipped examples, stage selection, prompt and configuration changes, pipeline migration, container retrieval, and output validation.
中文简介正在准备中。当前显示英语简介。
Deploy and manage NVIDIA RAG Blueprint, a system that retrieves information to support AI answers. Check the running environment, configure models and search features, troubleshoot unhealthy services, and verify affected workflows after changes.
中文简介正在准备中。当前显示英语简介。
Replace the object detector in VSS Alerts Blueprint verification mode with an ONNX model. This guide covers model placement, interpreting detection outputs, DeepStream configuration, TensorRT engine builds, redeployment, and common loading or mount failures.
中文简介正在准备中。当前显示英语简介。
Run a Kubernetes workflow that changes clothing in cropped person images, searches person attributes, and builds augmented datasets. The skill handles input preparation, run monitoring, and result retrieval for person re-identification data work.
中文简介正在准备中。当前显示英语简介。
Choose how to distribute tokens, the units a model processes, across MoE model experts during training. The guide compares alltoall, DeepEP, and HybridEP by GPU hardware, parallelism scale, memory needs, and optimization stage.
中文简介正在准备中。当前显示英语简介。
Measure language model response times and generation speed on Jetson using wrappers for vLLM, llama.cpp, or Ollama. Produces structured JSON results to assess models, power modes, runtime settings, and performance changes after tuning.
中文简介正在准备中。当前显示英语简介。
Provides instructions for serving language and vision-language models on Jetson with vLLM or SGLang. Selects a runtime for the device and JetPack version, supplies launch commands, and explains how to verify the OpenAI-compatible API.
中文简介正在准备中。当前显示英语简介。
Run an Isaac for Healthcare workflow from robot recordings through dataset preparation, policy training, and checkpoint validation. Uses the maintained pipeline driver, checks the planned commands first, and verifies artifacts and logs at each stage.
中文简介正在准备中。当前显示英语简介。
VLM indoor safety hazard detection benchmark inspired by HomeSafeBench (arXiv 2509.23690)
中文简介正在准备中。当前显示原文说明。
VLM evaluation suite for video anomaly detection in smart home camera footage
中文简介正在准备中。当前显示原文说明。
LLM & VLM evaluation suite for home security AI applications
中文简介正在准备中。当前显示原文说明。
Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".
中文简介正在准备中。当前显示原文说明。
对已完成分析的视频进行导演与剪辑策划，再写带时间戳的中文解说并校验；也处理已有短片的 宣发标题、花字修订和外部文案回填。普通策划输入 work_dir 的 agent_narration_brief.md 与 vlm_analysis.json；文案返修输入当前成片的工程与内容证据。策划输出 recap_story_plan.json、visual_audio_board.json、 可选 style_card.json、cut 模式需要的 clip_plan.json，以及通过校验的 narration.json；仅宣发文案任务交付提案或回填既有包装计划。 外发说明：只有建议型评审 review.py 联网，它把旁白稿全文与理解证据、策划文件的文字摘录发到 MiMo chat 接口 （MIMO_API_KEY / MIMO_API_URL，不发视频、图片或音频）；单独使用时只在显式执行时运行，端到端编排默认在 TTS 前运行一次， 可用 --no-review-narration / REVIEW_NARRATION=0 关闭（严格评审开启时除外）；validate.py 与 lint 仅在本地运行。 触发词：解说词、写解说、视频旁白、宣发标题、花字修订、文案回填、 narration script、写稿、解说文案、剪辑思路、导演思路。
中文简介正在准备中。当前显示原文说明。
视频多模态理解：对视频生成描述/摘要/标签，并支持基于视频内容问答。当用户要理解视频内容、生成描述或对视频提问时触发。
中文简介正在准备中。当前显示原文说明。
Reads or converts documents in a research workflow, including PDF, Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, and CSV. Chooses direct reading or conversion, selects a converter from document structure, and decides whether the Markdown is tracked or temporary. Use when a document must be read, quoted, summarized, searched, extracted, or added to a source library. Scanned documents go to vlm-ocr and bulk intake to research-repo.
中文简介正在准备中。当前显示原文说明。
Read or convert documents (PDF, Office, OpenDocument, RTF, EPUB, CSV) in a research workflow: read directly or convert, pick the converter from document structure, and decide whether the Markdown is tracked or scratch. Use when a document must be read, quoted, summarized, searched, extracted, or added to a source library; scans go to $vlm-ocr.
中文简介正在准备中。当前显示原文说明。
Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".
中文简介正在准备中。当前显示原文说明。
执行模型测评（统一入口）。LLM/VLM 走主流程 scripts/run_evaluation.py + Evaluation YAML；model_family=dit 走 DiT 扩展节（references/dit/evaluate_workflow.md，vbench.py 批量推理产出视频）。
中文简介正在准备中。当前显示原文说明。
为 msModelSlim 创建基础 Transformers 模型适配器（Model Adapter）。 包含创建适配器、实现必需接口与注册安装流程。 适用：Decoder-only LLM、理解类 VLM（仅 LLM/text 部分）。 多模态生成（DiT/扩散，含双/多专家）见下方「多模态生成扩展」节，按需加载。 不适用：Encoder-only、非 Transformers 架构。
中文简介正在准备中。当前显示原文说明。
AI 视频生成全流程：通过 6 个阶段（剧本→角色/场景设计→分镜→参考图→视频生成→后期剪辑）将用户想法转化为完整视频。支持临时工作台（单独调用 LLM、VLM、文生图、图生图、视频生成）和一次性短流程 Pipeline（文艺短视频、动作迁移、数字人口播）。触发词：视频生成、AI视频、AIGC、创作视频、制作视频、AI画图、文艺短视频、静态短视频、动作迁移、数字人口播。
中文简介正在准备中。当前显示原文说明。
Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).
中文简介正在准备中。当前显示原文说明。
Avalia LLMs em 100+ benchmarks de 18+ harnesses (MMLU, HumanEval, GSM8K, segurança, VLM) com execução multi-backend. Use quando precisar de avaliação escalável em Docker local, HPC Slurm ou plataformas cloud. Plataforma enterprise-grade da NVIDIA com arquitetura container-first para benchmarking reproduzível.
中文简介正在准备中。当前显示原文说明。