# NVIDIA

## Models

- [Active Speaker Detection](/qc69jvmznzxy/active-speaker-detection.md) — Detect and track speaker identities across video frames.
- [Background Noise Removal](/qc69jvmznzxy/bnr.md) — Removes unwanted noises from audio improving speech intelligibility.
- [bevformer](/qc69jvmznzxy/bevformer.md) — Advanced transformer for multi-frame bird's-eye-view 3D perception in autonomous driving.
- [canary-1b-asr](/qc69jvmznzxy/canary-1b-asr.md) — Multi-lingual model supporting speech-to-text recognition and translation.
- [conformer-ctc-asr](/qc69jvmznzxy/conformer-ctc-asr.md) — Automatic speech recognition model that transcribes speech in lower case Spanish with record-setting accuracy and performance
- [cosmos-transfer2.5-2b](/qc69jvmznzxy/cosmos-transfer2_5-2b.md) — Generates physics-aware video world states for physical AI development using text prompts and multiple spatial control inputs derived from real-world data or simulation.
- [cosmos3-nano](/qc69jvmznzxy/cosmos3-nano.md) — Generates physics-aware videos from text prompts or an image prompt for physical AI development.
- [cosmos3-nano-reasoner](/qc69jvmznzxy/cosmos3-nano-reasoner.md) — Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
- [cuopt](/qc69jvmznzxy/nvidia-cuopt.md) — World-record accuracy and performance for complex route optimization.
- [eyecontact](/qc69jvmznzxy/eyecontact.md) — Estimate gaze angles of a person in a video and redirect to make it frontal.
- [fourcastnet](/qc69jvmznzxy/fourcastnet.md) — FourCastNet predicts global atmospheric dynamics of various weather / climate variables.
- [genmol](/qc69jvmznzxy/genmol-generate.md) — Fragment-Based Molecular Generation by Discrete Diffusion.
- [ising-calibration-1-35b-a3b](/qc69jvmznzxy/ising-calibration-1-35b-a3b.md) — Open VLM for quantum computer calibration chart understanding across a range of qubit modalities.
- [ising-calibration-1.5-31b](/qc69jvmznzxy/ising-calibration-1.5-31b.md) — NVIDIA-Ising-Calibration-1.5 is a dense multimodal vision-language model built on Gemma 4 31B. It analyzes quantum computing calibration experiment plots and generates structured technical text.
- [Kumo Relational](/qc69jvmznzxy/kumo-relational.md) — A relational foundation model for prediction over structured, multi-table data.
- [LipSync](/qc69jvmznzxy/lipsync.md) — Generative lip dubbing that syncs lips in a video to input audio.
- [llama-3.1-nemoguard-8b-content-safety](/qc69jvmznzxy/llama-3_1-nemoguard-8b-content-safety.md) — Leading content safety model for enhancing the safety and moderation capabilities of LLMs
- [llama-3.1-nemoguard-8b-topic-control](/qc69jvmznzxy/llama-3_1-nemoguard-8b-topic-control.md) — Topic control model to keep conversations focused on approved topics, avoiding inappropriate content.
- [llama-3.1-nemotron-safety-guard-8b-v3](/qc69jvmznzxy/llama-3_1-nemotron-safety-guard-8b-v3.md) — Leading multilingual content safety model for enhancing the safety and moderation capabilities of LLMs
- [llama-nemotron-embed-vl-1b-v2](/qc69jvmznzxy/llama-nemotron-embed-vl-1b-v2.md) — Multimodal question-answer retrieval representing user queries as text and documents as images.
- [llama-nemotron-rerank-vl-1b-v2](/qc69jvmznzxy/llama-nemotron-rerank-vl-1b-v2.md) — GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.
- [magpie-tts-multilingual](/qc69jvmznzxy/magpie-tts-multilingual.md) — Natural and expressive voices in multiple languages. For voice agents and brand ambassadors.
- [magpie-tts-zeroshot](/qc69jvmznzxy/magpie-tts-zeroshot.md) — Expressive and engaging text-to-speech, generated from a short audio sample.
- [megatron-1b-nmt](/qc69jvmznzxy/megatron-1b-nmt.md) — Enable smooth global interactions in 36 languages.
- [molmim](/qc69jvmznzxy/molmim-generate.md) — MolMIM performs controlled generation, finding molecules with the right properties.
- [nemoguard-jailbreak-detect](/qc69jvmznzxy/nemoguard-jailbreak-detect.md) — Industry leading jailbreak classification model for protection from adversarial attempts
- [nemoretriever-ocr](/qc69jvmznzxy/nemoretriever-ocr.md) — Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.
- [nemotron-3-embed-1b](/qc69jvmznzxy/nemotron-3-embed-1b.md) — 1B embedding model for semantic search, retrieval, and RAG applications.
- [nemotron-3-nano-omni-30b-a3b-reasoning](/qc69jvmznzxy/nemotron-3-nano-omni-30b-a3b-reasoning.md) — Nemotron 3 Nano Omni is an omni-modal reasoning model that understands images, video, speech, text.
- [nemotron-3-super-120b-a12b](/qc69jvmznzxy/nemotron-3-super-120b-a12b.md) — Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
- [nemotron-3-ultra-550b-a55b](/qc69jvmznzxy/nemotron-3-ultra-550b-a55b.md) — Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
- [nemotron-3.5-content-safety](/qc69jvmznzxy/nemotron-3.5-content-safety.md) — Multilingual, multimodal model for detecting unsafe and toxic content.
- [nemotron-3.5-lightning-30b-a3b](/qc69jvmznzxy/nemotron-3.5-lightning-30b-a3b.md) — Fastest 30B A3B MoE model with leading domain accuracy for specialized agentic tasks
- [nemotron-asr-streaming](/qc69jvmznzxy/nemotron-asr-streaming.md) — Real-time speech recognition for English
- [nemotron-graphic-elements-v1](/qc69jvmznzxy/nemotron-graphic-elements-v1.md) — Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
- [nemotron-ocr-v1](/qc69jvmznzxy/nemotron-ocr-v1.md) — Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.
- [nemotron-ocr-v2](/qc69jvmznzxy/nemotron-ocr-v2.md) — Nemotron OCR v2 is a state-of-the-art multilingual text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images.
- [nemotron-page-elements-v3](/qc69jvmznzxy/nemotron-page-elements-v3.md) — Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
- [nemotron-parse](/qc69jvmznzxy/nemotron-parse.md) — Cutting-edge vision-language model exceling in retrieving text and metadata from images.
- [nemotron-parse-2.0](/qc69jvmznzxy/nemotron-parse-2.0.md) — Cutting-edge vision-language model excelling in retrieving text and metadata from images.
- [nemotron-table-structure-v1](/qc69jvmznzxy/nemotron-table-structure-v1.md) — Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
- [nemotron-voicechat](/qc69jvmznzxy/nemotron-voicechat.md) — Nemotron 3 Voicechat
- [parakeet-1.1b-rnnt-multilingual-asr](/qc69jvmznzxy/parakeet-1_1b-rnnt-multilingual-asr.md) — High accuracy and optimized performance for transcription in 25 languages
- [parakeet-ctc-0.6b-asr](/qc69jvmznzxy/parakeet-ctc-0_6b-asr.md) — State-of-the-art accuracy and speed for English transcriptions.
- [parakeet-ctc-0.6b-es](/qc69jvmznzxy/parakeet-ctc-0_6b-es.md) — Accurate and optimized Spanish English transcriptions with punctuation and word timestamps.
- [parakeet-ctc-0.6b-vi](/qc69jvmznzxy/parakeet-ctc-0_6b-vi.md) — Accurate and optimized Vietnamese-English transcriptions with punctuation and word timestamps.
- [parakeet-ctc-0.6b-zh-cn](/qc69jvmznzxy/parakeet-ctc-0_6b-zh-cn.md) — Record-setting accuracy and performance for Mandarin English transcriptions.
- [parakeet-ctc-0.6b-zh-tw](/qc69jvmznzxy/parakeet-ctc-0_6b-zh-tw.md) — Record-setting accuracy and performance for Mandarin Taiwanese English transcriptions.
- [parakeet-ctc-1.1b-asr](/qc69jvmznzxy/parakeet-ctc-1_1b-asr.md) — Record-setting accuracy and performance for English transcription.
- [parakeet-tdt-0.6b](/qc69jvmznzxy/parakeet-tdt-0_6b.md) — Multilingual ASR across 25 European languages with punctuation, capitalization, and word timestamps
- [parakeet-tdt-0.6b-v2](/qc69jvmznzxy/parakeet-tdt-0_6b-v2.md) — Accurate and optimized English transcriptions with punctuation and word timestamps
- [qwen-image-edit-nvpcb-ovsl2sl](/qc69jvmznzxy/qwen-image-edit-nvpcb-ovsl2sl.md) — An image edit model specialized for Omniverse synthetic to photographic solder-light style captured at NVIDIA PCB inspection stations
- [Relighting](/qc69jvmznzxy/relighting.md) — Re-illuminate people in video to match target lighting from a 360 HDRI environment map.
- [riva-translate-1.6b](/qc69jvmznzxy/riva-translate-1_6b.md) — Enable smooth global interactions in 36 languages.
- [riva-translate-4b-instruct-v1_1](/qc69jvmznzxy/riva-translate-4b-instruct-v1_1.md) — Translation model in 12 languages with few-shots example prompts capability.
- [riva-translate-4b-instruct-v2](/qc69jvmznzxy/riva-translate-4b-instruct-v2.md) — Translation model in 37 languages with few-shots example prompts capability.
- [sparsedrive](/qc69jvmznzxy/sparsedrive.md) — End-to-end autonomous driving stack integrating perception, prediction, and planning with sparse scene representations for efficiency and safety.
- [streampetr](/qc69jvmznzxy/streampetr.md) — StreamPETR offers efficient 3D object detection for autonomous driving by propagating sparse object queries temporally.
- [Studio Voice](/qc69jvmznzxy/studiovoice.md) — Enhance input speech recorded with low-quality microphones in noisy or reverberant environments, producing studio-quality speech.
- [synthetic-video-detector](/qc69jvmznzxy/synthetic-video-detector.md) — NVIDIA Synthetic Video Detector is an AI-powered micro-service for detecting AI‑generated (synthetic) videos.
- [Video Super Resolution NIM](/qc69jvmznzxy/vsr.md) — Upscale encoded or ST 2110 video to higher resolutions with NVIDIA Video Super Resolution.
- [Active Speaker Detection](/qc69jvmznzxy/active-speaker-detection.md) — Detect and track speaker identities across video frames.
- [Background Noise Removal](/qc69jvmznzxy/bnr.md) — Removes unwanted noises from audio improving speech intelligibility.
- [bevformer](/qc69jvmznzxy/bevformer.md) — Advanced transformer for multi-frame bird's-eye-view 3D perception in autonomous driving.
- [canary-1b-asr](/qc69jvmznzxy/canary-1b-asr.md) — Multi-lingual model supporting speech-to-text recognition and translation.
- [conformer-ctc-asr](/qc69jvmznzxy/conformer-ctc-asr.md) — Automatic speech recognition model that transcribes speech in lower case Spanish with record-setting accuracy and performance
- [cosmos-transfer2.5-2b](/qc69jvmznzxy/cosmos-transfer2_5-2b.md) — Generates physics-aware video world states for physical AI development using text prompts and multiple spatial control inputs derived from real-world data or simulation.
- [cosmos3-nano](/qc69jvmznzxy/cosmos3-nano.md) — Generates physics-aware videos from text prompts or an image prompt for physical AI development.
- [cosmos3-nano-reasoner](/qc69jvmznzxy/cosmos3-nano-reasoner.md) — Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
- [cuopt](/qc69jvmznzxy/nvidia-cuopt.md) — World-record accuracy and performance for complex route optimization.
- [eyecontact](/qc69jvmznzxy/eyecontact.md) — Estimate gaze angles of a person in a video and redirect to make it frontal.
- [fourcastnet](/qc69jvmznzxy/fourcastnet.md) — FourCastNet predicts global atmospheric dynamics of various weather / climate variables.
- [genmol](/qc69jvmznzxy/genmol-generate.md) — Fragment-Based Molecular Generation by Discrete Diffusion.
- [ising-calibration-1-35b-a3b](/qc69jvmznzxy/ising-calibration-1-35b-a3b.md) — Open VLM for quantum computer calibration chart understanding across a range of qubit modalities.
- [ising-calibration-1.5-31b](/qc69jvmznzxy/ising-calibration-1.5-31b.md) — NVIDIA-Ising-Calibration-1.5 is a dense multimodal vision-language model built on Gemma 4 31B. It analyzes quantum computing calibration experiment plots and generates structured technical text.
- [Kumo Relational](/qc69jvmznzxy/kumo-relational.md) — A relational foundation model for prediction over structured, multi-table data.
- [LipSync](/qc69jvmznzxy/lipsync.md) — Generative lip dubbing that syncs lips in a video to input audio.
- [llama-3.1-nemoguard-8b-content-safety](/qc69jvmznzxy/llama-3_1-nemoguard-8b-content-safety.md) — Leading content safety model for enhancing the safety and moderation capabilities of LLMs
- [llama-3.1-nemoguard-8b-topic-control](/qc69jvmznzxy/llama-3_1-nemoguard-8b-topic-control.md) — Topic control model to keep conversations focused on approved topics, avoiding inappropriate content.
- [llama-3.1-nemotron-safety-guard-8b-v3](/qc69jvmznzxy/llama-3_1-nemotron-safety-guard-8b-v3.md) — Leading multilingual content safety model for enhancing the safety and moderation capabilities of LLMs
- [llama-nemotron-embed-vl-1b-v2](/qc69jvmznzxy/llama-nemotron-embed-vl-1b-v2.md) — Multimodal question-answer retrieval representing user queries as text and documents as images.
- [llama-nemotron-rerank-vl-1b-v2](/qc69jvmznzxy/llama-nemotron-rerank-vl-1b-v2.md) — GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.
- [magpie-tts-multilingual](/qc69jvmznzxy/magpie-tts-multilingual.md) — Natural and expressive voices in multiple languages. For voice agents and brand ambassadors.
- [magpie-tts-zeroshot](/qc69jvmznzxy/magpie-tts-zeroshot.md) — Expressive and engaging text-to-speech, generated from a short audio sample.
- [megatron-1b-nmt](/qc69jvmznzxy/megatron-1b-nmt.md) — Enable smooth global interactions in 36 languages.
- [molmim](/qc69jvmznzxy/molmim-generate.md) — MolMIM performs controlled generation, finding molecules with the right properties.
- [nemoguard-jailbreak-detect](/qc69jvmznzxy/nemoguard-jailbreak-detect.md) — Industry leading jailbreak classification model for protection from adversarial attempts
- [nemoretriever-ocr](/qc69jvmznzxy/nemoretriever-ocr.md) — Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.
- [nemotron-3-embed-1b](/qc69jvmznzxy/nemotron-3-embed-1b.md) — 1B embedding model for semantic search, retrieval, and RAG applications.
- [nemotron-3-nano-omni-30b-a3b-reasoning](/qc69jvmznzxy/nemotron-3-nano-omni-30b-a3b-reasoning.md) — Nemotron 3 Nano Omni is an omni-modal reasoning model that understands images, video, speech, text.
- [nemotron-3-super-120b-a12b](/qc69jvmznzxy/nemotron-3-super-120b-a12b.md) — Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
- [nemotron-3-ultra-550b-a55b](/qc69jvmznzxy/nemotron-3-ultra-550b-a55b.md) — Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
- [nemotron-3.5-content-safety](/qc69jvmznzxy/nemotron-3.5-content-safety.md) — Multilingual, multimodal model for detecting unsafe and toxic content.
- [nemotron-3.5-lightning-30b-a3b](/qc69jvmznzxy/nemotron-3.5-lightning-30b-a3b.md) — Fastest 30B A3B MoE model with leading domain accuracy for specialized agentic tasks
- [nemotron-asr-streaming](/qc69jvmznzxy/nemotron-asr-streaming.md) — Real-time speech recognition for English
- [nemotron-graphic-elements-v1](/qc69jvmznzxy/nemotron-graphic-elements-v1.md) — Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
- [nemotron-ocr-v1](/qc69jvmznzxy/nemotron-ocr-v1.md) — Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.
- [nemotron-ocr-v2](/qc69jvmznzxy/nemotron-ocr-v2.md) — Nemotron OCR v2 is a state-of-the-art multilingual text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images.
- [nemotron-page-elements-v3](/qc69jvmznzxy/nemotron-page-elements-v3.md) — Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
- [nemotron-parse](/qc69jvmznzxy/nemotron-parse.md) — Cutting-edge vision-language model exceling in retrieving text and metadata from images.
- [nemotron-parse-2.0](/qc69jvmznzxy/nemotron-parse-2.0.md) — Cutting-edge vision-language model excelling in retrieving text and metadata from images.
- [nemotron-table-structure-v1](/qc69jvmznzxy/nemotron-table-structure-v1.md) — Model for object detection, fine-tuned to detect charts, tables, and titles in documents.
- [nemotron-voicechat](/qc69jvmznzxy/nemotron-voicechat.md) — Nemotron 3 Voicechat
- [parakeet-1.1b-rnnt-multilingual-asr](/qc69jvmznzxy/parakeet-1_1b-rnnt-multilingual-asr.md) — High accuracy and optimized performance for transcription in 25 languages
- [parakeet-ctc-0.6b-asr](/qc69jvmznzxy/parakeet-ctc-0_6b-asr.md) — State-of-the-art accuracy and speed for English transcriptions.
- [parakeet-ctc-0.6b-es](/qc69jvmznzxy/parakeet-ctc-0_6b-es.md) — Accurate and optimized Spanish English transcriptions with punctuation and word timestamps.
- [parakeet-ctc-0.6b-vi](/qc69jvmznzxy/parakeet-ctc-0_6b-vi.md) — Accurate and optimized Vietnamese-English transcriptions with punctuation and word timestamps.
- [parakeet-ctc-0.6b-zh-cn](/qc69jvmznzxy/parakeet-ctc-0_6b-zh-cn.md) — Record-setting accuracy and performance for Mandarin English transcriptions.
- [parakeet-ctc-0.6b-zh-tw](/qc69jvmznzxy/parakeet-ctc-0_6b-zh-tw.md) — Record-setting accuracy and performance for Mandarin Taiwanese English transcriptions.
- [parakeet-ctc-1.1b-asr](/qc69jvmznzxy/parakeet-ctc-1_1b-asr.md) — Record-setting accuracy and performance for English transcription.
- [parakeet-tdt-0.6b](/qc69jvmznzxy/parakeet-tdt-0_6b.md) — Multilingual ASR across 25 European languages with punctuation, capitalization, and word timestamps
- [parakeet-tdt-0.6b-v2](/qc69jvmznzxy/parakeet-tdt-0_6b-v2.md) — Accurate and optimized English transcriptions with punctuation and word timestamps
- [qwen-image-edit-nvpcb-ovsl2sl](/qc69jvmznzxy/qwen-image-edit-nvpcb-ovsl2sl.md) — An image edit model specialized for Omniverse synthetic to photographic solder-light style captured at NVIDIA PCB inspection stations
- [Relighting](/qc69jvmznzxy/relighting.md) — Re-illuminate people in video to match target lighting from a 360 HDRI environment map.
- [riva-translate-1.6b](/qc69jvmznzxy/riva-translate-1_6b.md) — Enable smooth global interactions in 36 languages.
- [riva-translate-4b-instruct-v1_1](/qc69jvmznzxy/riva-translate-4b-instruct-v1_1.md) — Translation model in 12 languages with few-shots example prompts capability.
- [riva-translate-4b-instruct-v2](/qc69jvmznzxy/riva-translate-4b-instruct-v2.md) — Translation model in 37 languages with few-shots example prompts capability.
- [sparsedrive](/qc69jvmznzxy/sparsedrive.md) — End-to-end autonomous driving stack integrating perception, prediction, and planning with sparse scene representations for efficiency and safety.
- [streampetr](/qc69jvmznzxy/streampetr.md) — StreamPETR offers efficient 3D object detection for autonomous driving by propagating sparse object queries temporally.
- [Studio Voice](/qc69jvmznzxy/studiovoice.md) — Enhance input speech recorded with low-quality microphones in noisy or reverberant environments, producing studio-quality speech.
- [synthetic-video-detector](/qc69jvmznzxy/synthetic-video-detector.md) — NVIDIA Synthetic Video Detector is an AI-powered micro-service for detecting AI‑generated (synthetic) videos.
- [Video Super Resolution NIM](/qc69jvmznzxy/vsr.md) — Upscale encoded or ST 2110 video to higher resolutions with NVIDIA Video Super Resolution.

## Blueprints

- [AI Agent for Telecom Network Configuration Planning](/qc69jvmznzxy/telco-network-configuration.md) — Automate and optimize the configuration of radio access network (RAN) parameters using agentic AI and a large language model (LLM)-driven framework.
- [AI Model Distillation for Financial Data](/qc69jvmznzxy/ai-model-distillation-for-financial-data.md) — Distill and deploy domain-specific AI models from unstructured financial data to generate market signals efficiently—scaling your workflow with the NVIDIA Data Flywheel Blueprint for high-performance, cost-efficient experimentation.
- [Ambient Healthcare Agents](/qc69jvmznzxy/ambient-healthcare-agents.md) — Build advanced AI agents for providers and patients using this developer example powered by NeMo Microservices, NVIDIA Nemotron, Riva ASR and TTS, and NVIDIA LLM NIM
- [Build a Digital Twin for Interactive Fluid Simulation](/qc69jvmznzxy/digital-twins-for-fluid-simulation.md) — This NVIDIA Omniverse™ Blueprint demonstrates how commercial software vendors can create interactive digital twins.
- [Build A Generative Protein Binder Design Pipeline](/qc69jvmznzxy/protein-binder-design-for-drug-discovery.md) — This blueprint shows how generative AI and accelerated NIM microservices can design protein binders smarter and faster.
- [Build A Generative Virtual Screening Pipeline](/qc69jvmznzxy/generative-virtual-screening-for-drug-discovery.md) — This blueprint shows how generative AI and accelerated NIM microservices can design optimized small molecules smarter and faster.
- [Build a Video Search and Summarization (VSS) Agent](/qc69jvmznzxy/video-search-and-summarization.md) — Ingest massive volumes of live or archived videos and extract insights for summarization and interactive Q&A
- [Build an Enterprise RAG Pipeline Blueprint](/qc69jvmznzxy/build-an-enterprise-rag-pipeline.md) — Power fast, accurate semantic search across multimodal enterprise data with NVIDIA’s RAG Blueprint—built on NeMo Retriever and Nemotron models—to connect your agents to trusted, authoritative sources of knowledge.
- [Build Your Own Transaction Foundation Model](/qc69jvmznzxy/build-your-own-transaction-foundation-model.md) — Create intelligent embeddings by using transformer architecture on tabular data.
- [Content Localization](/qc69jvmznzxy/content-localization.md) — Localize and translate media and sync multiple speaker’s lips to translated audio.
- [Cosmos Dataset Search](/qc69jvmznzxy/cosmos-dataset-search.md) — Accelerate post-training of end-to-end autonomous vehicle stacks with vector search and retrieval for large video datasets.
- [Evo 2 Protein Design](/qc69jvmznzxy/evo2-protein-design.md) — This workflow shows how generative AI can generate DNA sequences that can be translated into proteins for bioengineering.
- [Financial Fraud Detection](/qc69jvmznzxy/financial-fraud-detection.md) — Detect and prevent sophisticated fraudulent activities for financial services with high accuracy.
- [Genomic Analysis](/qc69jvmznzxy/genomics-analysis.md) — Easily run essential genomics workflows to save time leveraging Parabricks and CodonFM.
- [GPU Query Engine (GQE)](/qc69jvmznzxy/gpu-query-engine.md) — Build a GPU-accelerated SQL engine using NVIDIA's GQE reference architecture and libcudf with NVIDIA's open-source C++ APIs.
- [Multi-Agent Intelligent Warehouse](/qc69jvmznzxy/multi-agent-intelligent-warehouse.md) — An AI-powered, multi-agent system designed to optimize warehouse operations through intelligent automation, real-time monitoring, and natural language interaction.
- [NemoClaw for Hermes Agent](/qc69jvmznzxy/nemoclaw-for-hermes-agent.md) — Deploy Hermes agents that learn from team workflows, create reusable skills, and get better with every interaction.
- [NemoClaw for LangChain Deep Agents Code](/qc69jvmznzxy/nemoclaw-for-langchain-deep-agents-code.md) — Run open-source Deep Agents Code, tuned for Nemotron 3 Ultra, to plan, edit and test code with enterprise governance.
- [NemoClaw for OpenClaw](/qc69jvmznzxy/nemoclaw-for-openclaw.md) — Run always-on agents with greater control, privacy, and flexibility—installed with a single command.
- [Nemotron Voice Agent](/qc69jvmznzxy/nemotron-voice-agent.md) — Build Real-Time, Multimodal Voice Agents with NVIDIA Nemotron NIM.
- [Nsight Copilot - AI Code Assistant for CUDA Development](/qc69jvmznzxy/nsight-copilot.md) — Deploy an AI-powered coding assistant on DGX Spark that delivers expert CUDA-aware chat, real-time code completion, and retrieval-augmented generation grounded in authoritative GPU programming knowledge—powered by NVIDIA NIM microservices.
- [NVIDIA AI-Q Blueprint for intelligent agents](/qc69jvmznzxy/aiq.md) — AI agents that connect, retrieve, and reason on enterprise data—making information accessible, actionable, and intelligent.
- [NVIDIA Omniverse DSX Blueprint for AI Factory Digital Twins](/qc69jvmznzxy/omniverse-dsx-blueprint-for-ai-factories.md) — Design, simulate, and optimize AI factory infrastructure with digital twins.
- [Quantitative Portfolio Optimization](/qc69jvmznzxy/quantitative-portfolio-optimization.md) — Enable fast, scalable, and real-time portfolio optimization for financial institutions.
- [Quantitative Signal Discovery Agent](/qc69jvmznzxy/quantitative-signal-discovery-agent.md) — Automate and scale the discovery, testing, and refinement of trading signals for quantitative research.
- [Retail Agentic Commerce](/qc69jvmznzxy/retail-agentic-commerce.md) — Reference implementation of the Agentic Commerce Protocol (ACP) and Universal Commerce Protocol (UCP) enabling AI-powered checkout negotiation while maintaining merchant of record.
- [Retail Catalog Enrichment](/qc69jvmznzxy/retail-catalog-enrichment.md) — A GenAI system that enhances and localizes product catalogs with rich text content and imagery.
- [Retail Shopping Assistant](/qc69jvmznzxy/retail-shopping-assistant.md) — Elevate Shopping Experiences Online and In Stores.
- [Single Cell Analysis](/qc69jvmznzxy/single-cell-analysis.md) — Investigate, understand, and interpret single-cell data in minutes, not days, by leveraging RAPIDS-singlecell, powered by NVIDIA CUDA-X Data Science (RAPIDS™).
- [Streaming Data to RAG](/qc69jvmznzxy/streaming-data-to-rag.md) — Sensor-captured radio enables real-time awareness, AI-driven analytics for actionable, searchable insights.
- [Synthetic Manipulation Motion Generation for Robotics](/qc69jvmznzxy/isaac-gr00t-synthetic-manipulation.md) — Generate exponentially large amounts of synthetic motion trajectories for robot manipulation from just a few human demonstrations.
- [Vulnerability Analysis for Container Security](/qc69jvmznzxy/vulnerability-analysis-for-container-security.md) — Rapidly identify and mitigate container security vulnerabilities with generative AI.
- [AI Agent for Telecom Network Configuration Planning](/qc69jvmznzxy/telco-network-configuration.md) — Automate and optimize the configuration of radio access network (RAN) parameters using agentic AI and a large language model (LLM)-driven framework.
- [AI Model Distillation for Financial Data](/qc69jvmznzxy/ai-model-distillation-for-financial-data.md) — Distill and deploy domain-specific AI models from unstructured financial data to generate market signals efficiently—scaling your workflow with the NVIDIA Data Flywheel Blueprint for high-performance, cost-efficient experimentation.
- [Ambient Healthcare Agents](/qc69jvmznzxy/ambient-healthcare-agents.md) — Build advanced AI agents for providers and patients using this developer example powered by NeMo Microservices, NVIDIA Nemotron, Riva ASR and TTS, and NVIDIA LLM NIM
- [Build a Digital Twin for Interactive Fluid Simulation](/qc69jvmznzxy/digital-twins-for-fluid-simulation.md) — This NVIDIA Omniverse™ Blueprint demonstrates how commercial software vendors can create interactive digital twins.
- [Build A Generative Protein Binder Design Pipeline](/qc69jvmznzxy/protein-binder-design-for-drug-discovery.md) — This blueprint shows how generative AI and accelerated NIM microservices can design protein binders smarter and faster.
- [Build A Generative Virtual Screening Pipeline](/qc69jvmznzxy/generative-virtual-screening-for-drug-discovery.md) — This blueprint shows how generative AI and accelerated NIM microservices can design optimized small molecules smarter and faster.
- [Build a Video Search and Summarization (VSS) Agent](/qc69jvmznzxy/video-search-and-summarization.md) — Ingest massive volumes of live or archived videos and extract insights for summarization and interactive Q&A
- [Build an Enterprise RAG Pipeline Blueprint](/qc69jvmznzxy/build-an-enterprise-rag-pipeline.md) — Power fast, accurate semantic search across multimodal enterprise data with NVIDIA’s RAG Blueprint—built on NeMo Retriever and Nemotron models—to connect your agents to trusted, authoritative sources of knowledge.
- [Build Your Own Transaction Foundation Model](/qc69jvmznzxy/build-your-own-transaction-foundation-model.md) — Create intelligent embeddings by using transformer architecture on tabular data.
- [Content Localization](/qc69jvmznzxy/content-localization.md) — Localize and translate media and sync multiple speaker’s lips to translated audio.
- [Cosmos Dataset Search](/qc69jvmznzxy/cosmos-dataset-search.md) — Accelerate post-training of end-to-end autonomous vehicle stacks with vector search and retrieval for large video datasets.
- [Evo 2 Protein Design](/qc69jvmznzxy/evo2-protein-design.md) — This workflow shows how generative AI can generate DNA sequences that can be translated into proteins for bioengineering.
- [Financial Fraud Detection](/qc69jvmznzxy/financial-fraud-detection.md) — Detect and prevent sophisticated fraudulent activities for financial services with high accuracy.
- [Genomic Analysis](/qc69jvmznzxy/genomics-analysis.md) — Easily run essential genomics workflows to save time leveraging Parabricks and CodonFM.
- [GPU Query Engine (GQE)](/qc69jvmznzxy/gpu-query-engine.md) — Build a GPU-accelerated SQL engine using NVIDIA's GQE reference architecture and libcudf with NVIDIA's open-source C++ APIs.
- [Multi-Agent Intelligent Warehouse](/qc69jvmznzxy/multi-agent-intelligent-warehouse.md) — An AI-powered, multi-agent system designed to optimize warehouse operations through intelligent automation, real-time monitoring, and natural language interaction.
- [NemoClaw for Hermes Agent](/qc69jvmznzxy/nemoclaw-for-hermes-agent.md) — Deploy Hermes agents that learn from team workflows, create reusable skills, and get better with every interaction.
- [NemoClaw for LangChain Deep Agents Code](/qc69jvmznzxy/nemoclaw-for-langchain-deep-agents-code.md) — Run open-source Deep Agents Code, tuned for Nemotron 3 Ultra, to plan, edit and test code with enterprise governance.
- [NemoClaw for OpenClaw](/qc69jvmznzxy/nemoclaw-for-openclaw.md) — Run always-on agents with greater control, privacy, and flexibility—installed with a single command.
- [Nemotron Voice Agent](/qc69jvmznzxy/nemotron-voice-agent.md) — Build Real-Time, Multimodal Voice Agents with NVIDIA Nemotron NIM.
- [Nsight Copilot - AI Code Assistant for CUDA Development](/qc69jvmznzxy/nsight-copilot.md) — Deploy an AI-powered coding assistant on DGX Spark that delivers expert CUDA-aware chat, real-time code completion, and retrieval-augmented generation grounded in authoritative GPU programming knowledge—powered by NVIDIA NIM microservices.
- [NVIDIA AI-Q Blueprint for intelligent agents](/qc69jvmznzxy/aiq.md) — AI agents that connect, retrieve, and reason on enterprise data—making information accessible, actionable, and intelligent.
- [NVIDIA Omniverse DSX Blueprint for AI Factory Digital Twins](/qc69jvmznzxy/omniverse-dsx-blueprint-for-ai-factories.md) — Design, simulate, and optimize AI factory infrastructure with digital twins.
- [Quantitative Portfolio Optimization](/qc69jvmznzxy/quantitative-portfolio-optimization.md) — Enable fast, scalable, and real-time portfolio optimization for financial institutions.
- [Quantitative Signal Discovery Agent](/qc69jvmznzxy/quantitative-signal-discovery-agent.md) — Automate and scale the discovery, testing, and refinement of trading signals for quantitative research.
- [Retail Agentic Commerce](/qc69jvmznzxy/retail-agentic-commerce.md) — Reference implementation of the Agentic Commerce Protocol (ACP) and Universal Commerce Protocol (UCP) enabling AI-powered checkout negotiation while maintaining merchant of record.
- [Retail Catalog Enrichment](/qc69jvmznzxy/retail-catalog-enrichment.md) — A GenAI system that enhances and localizes product catalogs with rich text content and imagery.
- [Retail Shopping Assistant](/qc69jvmznzxy/retail-shopping-assistant.md) — Elevate Shopping Experiences Online and In Stores.
- [Single Cell Analysis](/qc69jvmznzxy/single-cell-analysis.md) — Investigate, understand, and interpret single-cell data in minutes, not days, by leveraging RAPIDS-singlecell, powered by NVIDIA CUDA-X Data Science (RAPIDS™).
- [Streaming Data to RAG](/qc69jvmznzxy/streaming-data-to-rag.md) — Sensor-captured radio enables real-time awareness, AI-driven analytics for actionable, searchable insights.
- [Synthetic Manipulation Motion Generation for Robotics](/qc69jvmznzxy/isaac-gr00t-synthetic-manipulation.md) — Generate exponentially large amounts of synthetic motion trajectories for robot manipulation from just a few human demonstrations.
- [Vulnerability Analysis for Container Security](/qc69jvmznzxy/vulnerability-analysis-for-container-security.md) — Rapidly identify and mitigate container security vulnerabilities with generative AI.