NVIDIA Corporation

Diagnose slow loading, high memory use, and low frame rates in USD 3D scenes. It coordinates measurement, scene validation, and optimization, then produces reports comparing available before-and-after evidence and an optimized scene when changes are performed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate slow loading in USD scenes
• Diagnose low frame rates and high memory use
• Review repeated structures in large CAD scenes

Convert existing Hugging Face Trainer or TRL SFTTrainer code into an NVFLARE job for federated learning, where multiple sites train a shared model. Preserve training settings, validate locally, and export the resulting job.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Converting Trainer-based training into a federated job
• Adapting PEFT or LoRA fine-tuning for federated learning
• Preserving evaluation metrics during conversion

Switch the vision-language model, which handles images and text, in VSS Alerts Blueprint. Configure alert generation, verification, and agent queries separately, choose an external endpoint or bundled vLLM deployment, and verify an actual inference response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Switch all three VSS services to a different model endpoint
• Run standalone rtvi-vlm with an external model server
• Serve a model with vLLM inside the RTVI container

Fine-tune the MAISI VAE, a model that compresses and reconstructs CT or MRI volumes, using NIfTI datasets. Prepare training settings, check inputs before training, and save model checkpoints and loss histories for review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check a NIfTI dataset before GPU training
• Fine-tune a VAE with CT or MRI volumes
• Compare reconstruction losses across training runs

Set up NVIDIA infrastructure for synthetic data generation on MicroK8s or Azure AKS. Coordinate Kubernetes, inference services, and OSMO workflow execution, with prerequisite checks, deployment validation, capacity planning, and failure investigation before workloads are retried.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up a synthetic data generation environment on MicroK8s
• Deploy an Azure AKS environment with OSMO and inference services
• Check GPU quotas and capacity before scaling

Fine-tune NV-Segment-CT VISTA3D on CT images and region labels in NIfTI format. Choose standard training or fixed-class softmax training, save model checkpoints and evaluation records, and optionally track training with MLflow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tuning with paired CT images and region labels
• Checking the training workflow with a smoke run
• Training mutually exclusive classes with softmax

Find the right next step for an unclear NVFLARE request. Uses source or data inspection evidence to recommend a specific workflow skill for conversion, validation, deployment, or diagnosis, while keeping the project unchanged.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing where to start with NVFLARE
• Mapping a local project to a FLARE workflow
• Resolving unclear or conflicting training ownership

Investigate failures in NVIDIA TAO Visual ChangeNet classification experiments using prediction scores and actual images. Produces an illustrated root cause report covering data, reference images, training settings, and simulated changes to assess possible fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate missed defects and poor recall
• Analyze FAR regressions and false positives
• Audit reference images and inspection data

Generates a standalone YOLO26 detection and tracking service scaffold for VSS Search and Alerts. Includes DeepStream configuration, Docker files, and tests, with Kafka integration guidance and clear limits on validation before model assets are available.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a standalone YOLO26 service for VSS
• Generating a scaffold before model assets are ready
• Checking Kafka integration with VSS workflows

Evaluate answer quality in NVIDIA RAG Blueprint using local documents and question data. The skill guides dataset preparation, RAGAS scoring, configuration comparisons, and error diagnosis for RAG systems that retrieve documents to support generated answers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare documents and questions for evaluation
• Compare quality across retrieval and generation settings
• Interpret RAGAS result files

Find PhysicsNeMo models, data loading pipelines, and examples for machine learning tasks involving physical systems. The skill checks current repository files, presents relevant alternatives, and suggests a reading order without writing training code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding model families for physical forecasting
• Comparing models for grids and unstructured meshes
• Finding data loading pipelines for a dataset

Edit existing RTX Remix projects for classic DirectX 8/9 games through an MCP connection to the Toolkit. Replace models and textures, manage scene layers, and save and verify changes to captured game assets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Replacing textures in a classic game's Remix project
• Swapping captured models for existing replacement assets
• Organizing edits in scene layers

Create or refresh a governance card, a structured review document for an existing agent skill. It gathers local source evidence, renders a Markdown draft, and checks for unresolved review markers before submission for human review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a governance card for an existing skill
• Refresh a card after skill changes
• Prepare material for legal and safety review

Evaluate object detection predictions against labeled ground truth with TAO Data Services. Produce class-level precision, recall, accuracy, and AP, a detection quality measure, with CSV results and precision–recall plots for reviewing model performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Score object detection predictions against ground truth
• Review precision and recall by class
• Generate metrics CSV files and precision–recall plots

Find NVIDIA skills for a product or workflow using the current catalog. Get up to three relevant recommendations with reasons, installation commands, and starter prompts, or use an already installed skill when one fits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find skills for Jetson setup and troubleshooting
• Discover skills for CUDA or GPU development
• Identify skills for NeMo or NIM workflows

Find the right NVIDIA NuRec skills for turning sensor recordings into renderable 3D scenes. This routing guide organizes dataset downloads, conversion, training, rendering, and frame cleanup into workflows handled by separate specialist skills.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose the right NuRec skill
• Plan 3D reconstruction from sensor recordings
• Render a pretrained NuRec scene

Run NV-Segment-CTMR to divide CT or MRI NIfTI volumes into labeled regions. Save the label map and records of region volumes, processing time, and geometry checks for technical verification, without clinical interpretation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Automatically segmenting CT body volumes
• Segmenting body MRI or preprocessed brain MRI
• Requesting regions by specific label IDs

Investigate failed, stalled, or timed-out NVFLARE federated learning jobs, which coordinate training across sites. Collect limited logs and job artifacts, match known failure patterns, and report likely causes, confidence, and concrete recovery steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a failed local simulation
• Diagnosing stalled or timed-out jobs
• Checking client loss or EXECUTION_EXCEPTION errors

Turn records from a stopped NVFLARE Auto-FL optimization campaign into a reproducible Markdown report and JSON summary. Summarize improvements, retained candidates, failed ideas, and literature outcomes, with a refreshed progress plot when plotting dependencies are available.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a final report after an optimization campaign stops
• Summarize baseline scores and retained improvements
• Review successful and unsuccessful literature-based ideas

Compute statistics across distributed NVFLARE sites without sharing raw data. Generate and validate jobs for numeric tables or image datasets, then report site-level and global summaries, missing data rates, and applied privacy settings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing numeric data distributions across sites
• Computing means, variances, and quantiles across sites
• Summarizing image counts and pixel intensities

Generate synthetic 3D brain MRI volumes with NV-Generate-CTMR MR-Brain v1, choosing scan types such as T1 or FLAIR. The wrapper records generation settings and output checks for experimental review, with restrictions on clinical and production use.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generating synthetic T1 or T2 brain MRI volumes
• Trying FLAIR or SWI generation settings
• Specifying a random seed for generation

Integrate PhysicsNeMo domain parallelism, splitting one input across GPUs, into training or inference scripts. Guides DDP or FSDP2 integration, adds support for new operations, and checks distributed outputs and gradients against single-GPU results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Process inputs too large for one GPU
• Combine domain parallelism with DDP or FSDP2
• Add ShardTensor support for new operations

Operate NVIDIA App to check driver status, optimize games, and configure laptop features. Use its in-game overlay to record gameplay, save Instant Replay clips, capture screenshots, and control statistics visibility or RTX Dynamic Vibrance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check NVIDIA driver status and release notes
• Optimize settings for a game
• Record gameplay and save Instant Replay clips

Convert existing PyTorch training code into an NVFLARE federated learning job, where sites train with their own data. Adapt training and evaluation, exchange model updates through the Client API, validate locally, and export the job.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Convert a manual PyTorch training loop to federated learning
• Adapt existing evaluation code for federated rounds
• Validate and export a FedAvg training job