Conversational AI – NVIDIA Technical BlogNews and tutorials for developers, data scientists, and IT admins2025-04-29T22:44:15Zhttp://www.open-lab.net/blog/feed/Jonathan Bikoff<![CDATA[Spotlight: Personal AI Brings AI Receptionists to Small Business Owners with NVIDIA Riva]]>http://www.open-lab.net/blog/?p=994022025-04-29T22:44:15Z2025-04-29T22:44:07ZIt's 10 p.m. on a Tuesday when the phone rings at the Sapochnick Law Firm, a specialized law practice in San Diego, California. The caller, a client of the...
]]>1Brad Nemire<![CDATA[NVIDIA GTC Training Labs Now Available On Demand]]>http://www.open-lab.net/blog/?p=990742025-04-23T20:03:24Z2025-04-22T17:26:28ZMissed GTC? This year��s training labs are now available on demand to watch anywhere, anytime.
]]>Bartley Richardsonhttps://www.linkedin.com/in/bartleyrichardson/%20<![CDATA[Upcoming Event: NVIDIA Agent Toolkit Hackathon]]>http://www.open-lab.net/blog/?p=989652025-04-23T20:05:35Z2025-04-18T17:06:38ZBuild a high-performance agentic AI system using the open-source NVIDIA Agent Intelligence toolkit -- contest runs May 12 to May 23.
]]>Shai Shen-Orr<![CDATA[Curating Biological Findings from Scientific Literature with NVIDIA NIM]]>http://www.open-lab.net/blog/?p=985262025-04-28T23:18:36Z2025-04-10T18:30:00ZScientific papers are highly heterogeneous, often employing diverse terminologies for the same entities, using varied methodologies to study biological...
]]>Ashish Sardana<![CDATA[Prevent LLM Hallucinations with the Cleanlab Trustworthy Language Model in NVIDIA NeMo Guardrails]]>http://www.open-lab.net/blog/?p=984562025-04-22T23:39:03Z2025-04-09T20:00:00ZAs more enterprises integrate LLMs into their applications, they face a critical challenge: LLMs can generate plausible but incorrect responses, known as...
]]>Tyler Whitehouse<![CDATA[Just Released: NVIDIA AI Workbench 2025.03.10]]>http://www.open-lab.net/blog/?p=985492025-04-17T19:35:34Z2025-04-09T18:45:41ZNVIDIA AI Workbench 2025.03.10 features streamlined onboarding and enhanced UX for multicontainer projects.
]]>Anu Srivastava<![CDATA[NVIDIA Accelerates Inference on Meta Llama 4 Scout and Maverick]]>http://www.open-lab.net/blog/?p=984682025-04-22T23:57:03Z2025-04-06T02:18:34ZThe newest generation of the popular Llama AI models is here with Llama 4 Scout and Llama 4 Maverick. Accelerated by NVIDIA open-source software, they can...
]]>1Michelle Horton<![CDATA[Top Conversational AI Sessions at NVIDIA GTC 2025]]>http://www.open-lab.net/blog/?p=966942025-03-06T19:26:36Z2025-03-04T19:00:00ZLearn how to accelerate the full pipeline, from multilingual speech recognition and translation to generative AI and speech synthesis.
]]>Aditi Bodhankar<![CDATA[Measuring the Effectiveness and Performance of AI Guardrails in Generative AI Applications]]>http://www.open-lab.net/blog/?p=965622025-04-23T02:40:19Z2025-03-03T17:22:09ZSafeguarding AI agents and other conversational AI applications to ensure safe, on-brand and reliable behavior is essential for enterprises. NVIDIA NeMo...
]]>Sangjune Park<![CDATA[Spotlight: NAVER Place Optimizes SLM-Based Vertical Services with NVIDIA TensorRT-LLM]]>http://www.open-lab.net/blog/?p=962792025-04-23T02:32:43Z2025-02-28T17:57:49ZNAVER is a popular South Korean search engine company that offers Naver Place, a geo-based service that provides detailed information about millions of...
]]>Yifan Wu<![CDATA[Accelerating Scientific Literature Reviews with NVIDIA NIM Microservices for LLMs]]>http://www.open-lab.net/blog/?p=963242025-04-23T02:38:59Z2025-02-26T17:00:00ZA well-crafted systematic review is often the initial step for researchers exploring a scientific field. For scientists new to this field, it provides a...
]]>Sven Chilton<![CDATA[Deploying NVIDIA Riva Multilingual ASR with Whisper and Canary Architectures While Selectively Deactivating NMT]]>http://www.open-lab.net/blog/?p=953392025-04-23T02:42:38Z2025-02-20T18:54:48ZNVIDIA has consistently developed automatic speech recognition (ASR) models that set the benchmark in the industry. Earlier versions of NVIDIA Riva, a...
]]>Cheng-Han (Hank) Du<![CDATA[Improving Translation Quality with Domain-Specific Fine-Tuning and NVIDIA NIM]]>http://www.open-lab.net/blog/?p=957562025-04-23T02:50:50Z2025-02-05T21:30:00ZTranslation plays an essential role in enabling companies to expand across borders, with requirements varying significantly in terms of tone, accuracy, and...
]]>1Dan Su<![CDATA[Announcing Nemotron-CC: A Trillion-Token English Language Dataset for LLM Pretraining]]>http://www.open-lab.net/blog/?p=948182025-01-23T19:54:30Z2025-01-09T19:20:16ZNVIDIA is excited to announce the release of Nemotron-CC, a 6.3-trillion-token English language Common Crawl dataset for pretraining highly accurate large...
]]>Brad Nemire<![CDATA[Upcoming Livestream: NVIDIA Developer Highlights from CES 2025]]>http://www.open-lab.net/blog/?p=948432025-01-23T19:54:32Z2025-01-09T10:00:00ZTune in January 16th at 9:00 AM PT for a live recap, followed by a Q&A of the latest developer announcements at CES 2025.
]]>Katie Link<![CDATA[Build a Generative AI Medical Device Training Assistant with NVIDIA NIM Microservices]]>http://www.open-lab.net/blog/?p=943792024-12-20T19:55:30Z2024-12-20T18:00:00ZInnovation in medical devices continues to accelerate, with a record number authorized by the FDA every year. When these new or updated devices are introduced...
]]>Joseph Lucas<![CDATA[Sandboxing Agentic AI Workflows with WebAssembly]]>http://www.open-lab.net/blog/?p=939752024-12-16T21:06:56Z2024-12-16T20:33:46ZAgentic AI workflows often involve the execution of large language model (LLM)-generated code to perform tasks like creating data visualizations. However, this...
]]>Isabel Hulseman<![CDATA[Three Building Blocks for Creating AI Virtual Assistants for Customer Service with an NVIDIA AI Blueprint]]>http://www.open-lab.net/blog/?p=906722024-12-12T19:35:14Z2024-12-11T23:49:16ZIn today's fast-paced business environment, providing exceptional customer service is no longer just a nice-to-have��it's a necessity. Whether addressing...
]]>Xin Dong<![CDATA[Hymba Hybrid-Head Architecture Boosts Small Language Model Performance]]>http://www.open-lab.net/blog/?p=925952024-12-12T19:38:36Z2024-11-22T17:31:14ZTransformers, with their attention-based architecture, have become the dominant choice for language models (LMs) due to their strong performance,...
]]>Xhoni Shollaj<![CDATA[Create a Custom Slackbot LLM Agent with NVIDIA NIM and LangChain]]>http://www.open-lab.net/blog/?p=898252025-02-17T05:12:38Z2024-11-19T17:00:00ZIn the dynamic world of modern business, where communication and efficient workflows are crucial for success, AI-powered solutions have become a competitive...
]]>1Chris Krapu<![CDATA[Creating RAG-Based Question-and-Answer LLM Workflows at NVIDIA]]>http://www.open-lab.net/blog/?p=908722024-11-11T20:00:23Z2024-10-28T16:00:00ZThe rapid development of solutions using retrieval augmented generation (RAG) for question-and-answer LLM workflows has led to new types of system...
]]>Maggie Zhang<![CDATA[Scaling LLMs with NVIDIA Triton and NVIDIA TensorRT-LLM Using Kubernetes]]>http://www.open-lab.net/blog/?p=904122025-03-18T18:18:17Z2024-10-22T16:53:55ZLarge language models (LLMs) have been widely used for chatbots, content generation, summarization, classification, translation, and more. State-of-the-art LLMs...
]]>Maryam Ashoori<![CDATA[IBM��s New Granite 3.0 Generative AI Models Are Small, Yet Highly Accurate and Efficient]]>http://www.open-lab.net/blog/?p=906362024-11-22T23:09:36Z2024-10-21T19:15:35ZToday, IBM released the third generation of IBM Granite, a collection of open language models and complementary tools. Prior generations of Granite focused on...
]]>Anurag Gudahttps://www.linkedin.com/in/anuragguda/<![CDATA[Simplify AI Application Development with NVIDIA Cloud Native Stack]]>http://www.open-lab.net/blog/?p=899702024-10-29T21:00:38Z2024-10-16T16:00:00ZIn the rapidly evolving landscape of AI and data science, the demand for scalable, efficient, and flexible infrastructure has never been higher. Traditional...
]]>Amit Bleiweiss<![CDATA[Evaluating Medical RAG with NVIDIA AI Endpoints and Ragas]]>http://www.open-lab.net/blog/?p=896252024-11-07T23:29:42Z2024-10-01T16:00:00ZIn the rapidly evolving field of medicine, the integration of cutting-edge technologies is crucial for enhancing patient care and advancing research. One such...
]]>Nick Comly<![CDATA[Low Latency Inference Chapter 2: Blackwell is Coming. NVIDIA GH200 NVL32 with NVLink Switch Gives Signs of Big Leap in Time to First Token Performance]]>http://www.open-lab.net/blog/?p=889382024-11-29T21:06:06Z2024-09-26T21:44:00ZMany of the most exciting applications of large language models (LLMs), such as interactive speech bots, coding co-pilots, and search, need to begin responding...
]]>Vinay Bagade<![CDATA[Build a Digital Human Interface for AI Apps with an NVIDIA NIM Agent Blueprint]]>http://www.open-lab.net/blog/?p=893452024-10-22T20:34:33Z2024-09-25T20:30:00ZProviding customers with quality service remains a top priority for businesses across industries, from answering questions and troubleshooting issues to...
]]>Anjali Shah<![CDATA[Deploying Accelerated Llama 3.2 from the Edge to the Cloud]]>http://www.open-lab.net/blog/?p=894362024-11-07T05:08:12Z2024-09-25T18:39:49ZExpanding the open-source Meta Llama collection of models, the Llama 3.2 collection includes vision language models (VLMs), small language models (SLMs), and an...
]]>Daniel Galvez<![CDATA[Accelerating Leaderboard-Topping ASR Models 10x with NVIDIA NeMo]]>http://www.open-lab.net/blog/?p=893302024-10-17T19:07:17Z2024-09-24T18:27:35ZNVIDIA NeMo has consistently developed automatic speech recognition (ASR) models that set the benchmark in the industry, particularly those topping the Hugging...
]]>Sven Chilton<![CDATA[Quickly Voice Your Apps with NVIDIA NIM Microservices for Speech and Translation]]>http://www.open-lab.net/blog/?p=891422024-09-19T20:17:19Z2024-09-18T22:48:43ZNVIDIA NIM, part of NVIDIA AI Enterprise, provides containers to self-host GPU-accelerated inferencing microservices for pretrained and customized AI models...
]]>Aaron Erickson<![CDATA[Optimizing Data Center Performance with AI Agents and the OODA Loop Strategy]]>http://www.open-lab.net/blog/?p=887292025-02-17T05:11:15Z2024-09-17T14:30:00ZFor any data center, operating large, complex GPU clusters is not for the faint of heart! There is a tremendous amount of complexity. Cooling, power,...
]]>10Jan Lasek<![CDATA[Post-Training Quantization of LLMs with NVIDIA NeMo and NVIDIA TensorRT Model Optimizer]]>http://www.open-lab.net/blog/?p=884892024-09-19T19:33:05Z2024-09-10T16:00:00ZAs large language models (LLMs) are becoming even bigger, it is increasingly important to provide easy-to-use and efficient deployment paths because the cost of...
]]>Sang-gil Lee<![CDATA[Achieving State-of-the-Art Zero-Shot Waveform Audio Generation across Audio Types]]>http://www.open-lab.net/blog/?p=883292024-09-19T19:34:33Z2024-09-05T20:30:00ZStunning audio content is an essential component of virtual worlds. Audio generative AI plays a key role in creating this content, and NVIDIA is continuously...
]]>Annamalai Chockalingam<![CDATA[Deploy Diverse AI Apps with Multi-LoRA Support on RTX AI PCs and Workstations]]>http://www.open-lab.net/blog/?p=880972024-11-14T16:09:00Z2024-08-28T13:00:00ZToday��s large language models (LLMs) achieve unprecedented results across many use cases. Yet, application developers often need to customize and tune these...
]]>Davide Tricarico<![CDATA[Enhancing RAG Applications with NVIDIA NIM]]>http://www.open-lab.net/blog/?p=877472024-10-28T21:55:21Z2024-08-27T16:00:00ZThe advent of large language models (LLMs) has significantly benefited the AI industry, offering versatile tools capable of generating human-like text and...
]]>Michelle Horton<![CDATA[Practical Strategies for Optimizing LLM Inference Sizing and Performance]]>http://www.open-lab.net/blog/?p=875112024-09-05T17:57:29Z2024-08-21T16:00:00ZAs the use of large language models (LLMs) grows across many applications, such as chatbots and content creation, it's important to understand the process of...
]]>Sama Bali<![CDATA[Hackathon: Build Groundbreaking Generative AI Projects Using NVIDIA AI Workbench]]>http://www.open-lab.net/blog/?p=877362024-09-05T17:57:30Z2024-08-20T20:04:23ZHosted by Dell and NVIDIA, demonstrate how AI Workbench can be used to build and deliver apps for a wide range of tasks and workflows.
]]>Ike Nnoli<![CDATA[Deploy the First On-Device Small Language Model for Improved Game Character Roleplay]]>http://www.open-lab.net/blog/?p=873022024-08-22T18:24:51Z2024-08-20T13:05:00ZAt Gamescom 2024, NVIDIA announced our first on-device small language model (SLM) for improving the conversation abilities of game characters. We also announced...
]]>Erin Ho<![CDATA[NVIDIA TensorRT Model Optimizer v0.15 Boosts Inference Performance and Expands Model Support]]>http://www.open-lab.net/blog/?p=872272024-08-22T18:24:54Z2024-08-15T17:11:37ZNVIDIA has announced the latest v0.15 release of NVIDIA TensorRT Model Optimizer, a state-of-the-art quantization toolkit of model optimization techniques...
]]>Sepi Motamedi<![CDATA[Video: Build Live Media Applications for AI-Enabled Infrastructure with NVIDIA Holoscan for Media]]>http://www.open-lab.net/blog/?p=872342024-11-04T22:50:16Z2024-08-14T17:35:11ZNVIDIA Holoscan for Media is a software-defined, AI-enabled platform that enables live video pipelines to run on the same infrastructure as AI. This video...
]]>Chintan Patel<![CDATA[New NIM Available: Mistral Large 2 Instruct LLM]]>http://www.open-lab.net/blog/?p=873082024-08-22T18:24:59Z2024-08-13T20:37:24ZThe new model by Mistral excels at a variety of complex tasks including text summarization, multilingual translation and reasoning, programming, question and...
]]>Hayden Wolff<![CDATA[Building AI Agents with NVIDIA NIM Microservices and LangChain]]>http://www.open-lab.net/blog/?p=865432024-10-28T21:55:34Z2024-08-07T16:00:00ZNVIDIA NIM, part of NVIDIA AI Enterprise, now supports tool-calling for models like Llama 3.1. It also integrates with LangChain to provide you with a...
]]>Kasikrit Chantharuang<![CDATA[Securing Generative AI Deployments with NVIDIA NIM and NVIDIA NeMo Guardrails]]>http://www.open-lab.net/blog/?p=866152024-11-20T19:58:44Z2024-08-05T20:30:00ZAs enterprises adopt generative AI applications powered by large language models (LLMs), there is an increasing need to implement guardrails to ensure safety...
]]>Sofia Kostandian<![CDATA[Developing Robust Georgian Automatic Speech Recognition with FastConformer Hybrid Transducer CTC BPE]]>http://www.open-lab.net/blog/?p=858352024-08-22T18:25:43Z2024-08-05T16:52:11ZBuilding an effective automatic speech recognition (ASR) model for underrepresented languages presents unique challenges due to limited data resources. In...
]]>Amit Bleiweiss<![CDATA[Enhancing RAG Pipelines with Re-Ranking]]>http://www.open-lab.net/blog/?p=860372024-10-28T21:56:26Z2024-07-30T16:00:00ZIn the rapidly evolving landscape of AI-driven applications, re-ranking has emerged as a pivotal technique to enhance the precision and relevance of enterprise...
]]>Yasmina Benkhoui<![CDATA[Spotlight: UneeQ Revolutionizes Customer Engagement with AI-Powered Digital Human Technology]]>http://www.open-lab.net/blog/?p=826622024-08-19T17:56:31Z2024-07-18T22:31:45ZWith the rise of chatbots and virtual assistants, customer interactions have evolved to embrace the versatility of voice and text inputs. However, integrating...
]]>Artem Chirkin<![CDATA[Accelerating Vector Search: NVIDIA cuVS IVF-PQ Part 2, Performance Tuning]]>http://www.open-lab.net/blog/?p=816812024-10-03T21:18:45Z2024-07-18T17:10:03ZIn the first part of the series, we presented an overview of the IVF-PQ algorithm and explained how it builds on top of the IVF-Flat algorithm, using the...
]]>Artem Chirkin<![CDATA[Accelerating Vector Search: NVIDIA cuVS IVF-PQ Part 1, Deep Dive]]>http://www.open-lab.net/blog/?p=816522024-10-03T21:19:09Z2024-07-18T17:09:45ZIn this post, we continue the series on accelerating vector search using NVIDIA cuVS. Our previous post in the series introduced IVF-Flat, a fast algorithm for...
]]>Ashraf Eassa<![CDATA[NVIDIA NeMo Accelerates LLM Innovation with Hybrid State Space Model Support]]>http://www.open-lab.net/blog/?p=856022024-08-08T18:48:47Z2024-07-17T17:32:08ZToday��s large language models (LLMs) are based on the transformer model architecture introduced in 2017. Since then, rapid advances in AI compute performance...
]]>1Tianna Nguy<![CDATA[New Workshops: Customize LLMs, Build and Deploy Large Neural Networks]]>http://www.open-lab.net/blog/?p=855052024-08-08T18:48:51Z2024-07-16T21:39:50ZRegister now for an instructor-led public workshop in July, August or September. Space is limited.
]]>Erin Ho<![CDATA[Train Generative AI Models More Efficiently with New NVIDIA Megatron-Core Functionalities]]>http://www.open-lab.net/blog/?p=849532024-07-25T18:14:45Z2024-07-12T22:25:42ZFirst introduced in 2019, NVIDIA Megatron-LM sparked a wave of innovation in the AI community, enabling researchers and developers to use the underpinnings of...
]]>Subhankar Ghosh<![CDATA[Addressing Hallucinations in Speech Synthesis LLMs with the NVIDIA NeMo T5-TTS Model]]>http://www.open-lab.net/blog/?p=845242024-07-25T18:19:15Z2024-07-02T20:00:00ZNVIDIA NeMo has released the T5-TTS model, a significant advancement in text-to-speech (TTS) technology. Based on large language models (LLMs), T5-TTS produces...
]]>Min-Hung Chenhttps://minhungchen.netlify.app/<![CDATA[Introducing DoRA, a High-Performing Alternative to LoRA for Fine-Tuning]]>http://www.open-lab.net/blog/?p=844542024-11-07T05:09:12Z2024-06-28T15:00:00ZFull fine-tuning (FT) is commonly employed to tailor general pretrained models for specific downstream tasks. To reduce the training cost, parameter-efficient...
]]>Hannah Simmons<![CDATA[Generate High-Quality, Context-Aware Responses for Chatbots and Search Engines with Llama 3-ChatQA]]>http://www.open-lab.net/blog/?p=845482024-07-10T15:28:34Z2024-06-26T16:44:52ZExperience and test Llama3-ChatQA models at scale with performance optimized NVIDIA NIM inference microservice using the NVIDIA API catalog.
]]>Elias Wolfberg<![CDATA[AI Brain Implant Restores Bilingual Communication for Stroke Survivor]]>http://www.open-lab.net/blog/?p=840402024-06-27T18:17:55Z2024-06-20T15:57:05ZScientists have enabled a stroke survivor, who is unable to speak, to communicate in both Spanish and English by training a neuroprosthesis implant to decode...
]]>Babak Hejazi<![CDATA[Introducing Grouped GEMM APIs in cuBLAS and More Performance Updates]]>http://www.open-lab.net/blog/?p=838882024-07-16T17:19:07Z2024-06-12T20:30:00ZThe latest release of NVIDIA cuBLAS library, version 12.5, continues to deliver functionality and performance to deep learning (DL) and high-performance...
]]>Tanay Varshney<![CDATA[NVIDIA Text Embedding Model Tops MTEB Leaderboard]]>http://www.open-lab.net/blog/?p=835712024-10-28T21:57:46Z2024-06-10T17:00:00ZThe latest embedding model from NVIDIA��NV-Embed��set a new record for embedding accuracy with a score of 69.32 on the Massive Text Embedding Benchmark...
]]>Ike Nnoli<![CDATA[Build Lifelike Digital Human Technology with NVIDIA ACE, Now Generally Available]]>http://www.open-lab.net/blog/?p=831732024-11-14T16:09:51Z2024-06-04T16:42:49ZNVIDIA ACE��a suite of generative AI-enabled digital human technologies��is now generally available for developers. Packaged as NVIDIA NIM microservices, ACE...
]]>Jesse Clayton<![CDATA[Streamline Development of AI-Powered Apps with NVIDIA RTX AI Toolkit for Windows RTX PCs]]>http://www.open-lab.net/blog/?p=831652024-11-14T16:10:37Z2024-06-02T12:30:00ZNVIDIA today launched the NVIDIA RTX AI Toolkit, a collection of tools and SDKs for Windows application developers to customize, optimize, and deploy AI models...
]]>Aditi Bodhankar<![CDATA[Building Safer LLM Apps with LangChain Templates and NVIDIA NeMo Guardrails]]>http://www.open-lab.net/blog/?p=830572025-02-04T19:52:06Z2024-05-31T21:37:43ZAn easily deployable reference architecture can help developers get to production faster with custom LLM use cases. LangChain Templates are a new way of...
]]>Nisanur Genc<![CDATA[Personalized Learning with Gipi, NVIDIA TensortRT-LLM, and AI Foundation Models]]>http://www.open-lab.net/blog/?p=829132024-05-30T19:55:44Z2024-05-30T16:00:00ZOver 1.2B people are actively learning new languages, with over 500M learners on digital learning platforms such as Duolingo. At the same time, a significant...
]]>Mitesh Patel<![CDATA[Generative AI Agents Developer Contest: Top Tips for Getting Started]]>http://www.open-lab.net/blog/?p=829802024-10-18T20:21:31Z2024-05-29T16:01:10ZJoin our contest that runs through June 17 and showcase your innovation using cutting-edge generative AI-powered applications using NVIDIA and LangChain...
]]>Matthew Nicely<![CDATA[Accelerating Transformers with NVIDIA cuDNN 9]]>http://www.open-lab.net/blog/?p=825922024-05-30T19:55:46Z2024-05-24T16:00:00ZThe NVIDIA CUDA Deep Neural Network library (cuDNN) is a GPU-accelerated library for accelerating deep learning primitives with state-of-the-art performance....
]]>1Nicole Luo<![CDATA[Training Localized Multilingual LLMs with NVIDIA NeMo, Part 2]]>http://www.open-lab.net/blog/?p=822952025-02-17T05:27:39Z2024-05-17T17:29:49ZIn Part 1, we discussed how to train a monolingual tokenizer and merge it with a pretrained LLM��s tokenizer to form a multilingual tokenizer. In this post, we...
]]>1Nicole Luo<![CDATA[Training Localized Multilingual LLMs with NVIDIA NeMo, Part 1]]>http://www.open-lab.net/blog/?p=822942024-10-18T20:22:45Z2024-05-17T17:29:13ZIn today's globalized world, the ability of AI systems to understand and communicate in diverse languages is increasingly crucial. Large language models (LLMs)...
]]>3Siddha Ganju<![CDATA[Develop Secure, Reliable Medical Apps with RAG and NVIDIA NeMo Guardrails]]>http://www.open-lab.net/blog/?p=825882025-02-04T19:52:46Z2024-05-15T20:00:00ZImagine an application that can sift through mountains of patient data, intelligently searching and answering questions about diagnoses, health histories, and...
]]>Zhiyong Ban<![CDATA[Customizing Neural Machine Translation Models with NVIDIA NeMo, Part 2]]>http://www.open-lab.net/blog/?p=821962025-02-17T05:23:38Z2024-05-13T17:17:38ZIn the first post, we walked through the prerequisites for a neural machine translation example from English to Chinese, running the pretrained model with NeMo,...
]]>Zhiyong Ban<![CDATA[Customizing Neural Machine Translation Models with NVIDIA NeMo, Part 1]]>http://www.open-lab.net/blog/?p=821952024-05-30T19:55:58Z2024-05-13T17:15:13ZNeural machine translation (NMT) is an automatic task of translating a sequence of words from one language to another. In recent years, the development of...
]]>Chintan Patel<![CDATA[Regional LLMs SEA-LION and SeaLLM Serve Languages and Cultures of Southeast Asia]]>http://www.open-lab.net/blog/?p=820142024-05-30T19:55:59Z2024-05-13T17:00:00ZAt the recent World Governments Summit in Dubai, NVIDIA CEO Jensen Huang emphasized the importance of sovereign AI, which refers to a nation��s capability to...
]]>Amit Bleiweiss<![CDATA[Tips for Building a RAG Pipeline with NVIDIA AI LangChain AI Endpoints]]>http://www.open-lab.net/blog/?p=818952025-03-11T16:19:32Z2024-05-08T16:00:00ZRetrieval-augmented generation (RAG) is a technique that combines information retrieval with a set of carefully designed system prompts to provide more...
]]>7Elena Rastorgueva<![CDATA[New Standard for Speech Recognition and Translation from the NVIDIA NeMo Canary Model]]>http://www.open-lab.net/blog/?p=806612024-08-06T17:19:16Z2024-04-18T20:09:33ZNVIDIA NeMo is an end-to-end platform for the development of multimodal generative AI models at scale anywhere��on any cloud and on-premises. The NeMo team...
]]>1Hainan Xu<![CDATA[Turbocharge ASR Accuracy and Speed with NVIDIA NeMo Parakeet-TDT]]>http://www.open-lab.net/blog/?p=807322024-08-12T16:06:21Z2024-04-18T20:03:54ZNVIDIA NeMo, an end-to-end platform for developing multimodal generative AI models at scale anywhere��on any cloud and on-premises��recently released...
]]>0Somshubra Majumdar<![CDATA[Pushing the Boundaries of Speech Recognition with NVIDIA NeMo Parakeet ASR Models]]>http://www.open-lab.net/blog/?p=805642024-08-12T16:07:43Z2024-04-18T20:03:07ZNVIDIA NeMo, an end-to-end platform for the development of multimodal generative AI models at scale anywhere��on any cloud and on-premises��released the...
]]>0Tiffany Yeung<![CDATA[Explainer: What Is a Convolutional Neural Network?]]>http://www.open-lab.net/blog/?p=759912024-06-05T22:20:53Z2024-04-12T19:00:00ZA convolutional neural network is a type of deep learning network used primarily to identify and classify images and to recognize objects within images.
]]>0Amanda Saunders<![CDATA[Develop Custom Enterprise Generative AI with NVIDIA NeMo]]>http://www.open-lab.net/blog/?p=803602025-02-17T05:27:49Z2024-03-27T20:00:00ZGenerative AI is transforming computing, paving new avenues for humans to interact with computers in natural, intuitive ways. For enterprises, the prospect of...
]]>Ike Nnoli<![CDATA[Generative AI for Digital Human Technologies and New AI-powered NVIDIA RTX Lighting]]>http://www.open-lab.net/blog/?p=797072024-12-09T16:51:28Z2024-03-19T17:00:00ZAt GDC 2024, NVIDIA announced that leading AI application developers such as Inworld AI are using NVIDIA digital human technologies to accelerate the deployment...
]]>Gordana Neskovic<![CDATA[NVIDIA Speech and Translation AI Models Set Records for Speed and Accuracy]]>http://www.open-lab.net/blog/?p=793652024-08-12T16:09:12Z2024-03-19T16:00:00ZSpeech and translation AI models developed at NVIDIA are pushing the boundaries of performance and innovation. The NVIDIA Parakeet automatic speech recognition...
]]>Chester Chen<![CDATA[Turning Machine Learning to Federated Learning in Minutes with NVIDIA FLARE 2.4]]>http://www.open-lab.net/blog/?p=788702024-05-10T00:20:39Z2024-03-07T00:39:33ZFederated learning (FL) is experiencing accelerated adoption due to its decentralized, privacy-preserving nature. In sectors such as healthcare and financial...
]]>Chintan Patel<![CDATA[Solve Complex AI Tasks with Leaderboard-Topping Smaug 72B from NVIDIA AI Foundation Models]]>http://www.open-lab.net/blog/?p=787692024-05-07T16:50:32Z2024-03-04T21:22:47ZThis week��s model release features the NVIDIA-optimized language model Smaug 72B, which you can experience directly from your browser. NVIDIA AI Foundation...
]]>Ziyue Xu<![CDATA[Scalable Federated Learning with NVIDIA FLARE for Enhanced LLM Performance]]>http://www.open-lab.net/blog/?p=783482024-05-10T00:21:02Z2024-02-29T21:00:00ZIn the ever-evolving landscape of large language models (LLMs), effective data management is a key challenge. Data is at the heart of model performance. While...
]]>0Tanya Lenz<![CDATA[Event: Speech and Generative AI Developer Day at NVIDIA GTC 2024]]>http://www.open-lab.net/blog/?p=786092024-03-07T19:29:14Z2024-02-29T21:00:00ZLearn how to build a RAG-powered application with a human voice interface at NVIDIA GTC 2024 Speech and Generative AI Developer Day.?
]]>0Chia-Chih Chen<![CDATA[Unlock Your LLM Coding Potential with StarCoder2]]>http://www.open-lab.net/blog/?p=785522024-03-07T19:32:10Z2024-02-28T14:00:00ZCoding is essential in the digital age, but it can also be tedious and time-consuming. That's why many developers are looking for ways to automate and...
]]>0Jess Nguyen<![CDATA[Video: Build a RAG-Powered Chatbot in Five Minutes]]>http://www.open-lab.net/blog/?p=782482024-05-02T16:46:56Z2024-02-27T21:30:00ZRetrieval-augmented generation (RAG) is exploding in popularity as a technique for boosting large language model (LLM) application performance. From highly...
]]>0Chintan Patel<![CDATA[Unlock the Power of Small Language Model Phi-2 for Chat, Research, Coding, and More]]>http://www.open-lab.net/blog/?p=784022024-06-06T14:55:12Z2024-02-27T18:00:39ZThis week��s model release features the NVIDIA-optimized language model Phi-2, which can be used for a wide range of natural language processing (NLP) tasks....
]]>0Michelle Horton<![CDATA[Top Inference for Large Language Models Sessions at NVIDIA GTC 2024]]>http://www.open-lab.net/blog/?p=777492024-02-22T19:58:59Z2024-02-13T17:00:00ZLearn how inference for LLMs is driving breakthrough performance for AI-enabled applications and services.
]]>0Brad Nemire<![CDATA[Featured Large Language Models Sessions at NVIDIA GTC 2024]]>http://www.open-lab.net/blog/?p=776492024-06-06T16:13:47Z2024-02-08T02:09:25ZSpeakers from NVIDIA, Meta, Microsoft, OpenAI, and ServiceNow will be talking about the latest tools, optimizations, trends and best practices for large...
]]>0Brad Nemire<![CDATA[Top Retrieval-Augmented Generation (RAG) Sessions at NVIDIA GTC 2024 Sessions]]>http://www.open-lab.net/blog/?p=775622024-06-06T16:14:28Z2024-02-06T19:38:44ZJoin us in-person or virtually and learn about the power of RAG with insights and best practices from experts at NVIDIA, visionary CEOs, data scientists, and...
]]>0Chintan Patel<![CDATA[Generate Code, Answer Queries, and Translate Text with New NVIDIA AI Foundation Models]]>http://www.open-lab.net/blog/?p=773642024-05-07T19:14:10Z2024-02-05T18:48:17ZThis week��s Model Monday release features the NVIDIA-optimized code Llama, Kosmos-2, and SeamlessM4T, which you can experience directly from your browser....
]]>0Amit Bleiweiss<![CDATA[Deploy an AI Coding Assistant with NVIDIA TensorRT-LLM and NVIDIA Triton]]>http://www.open-lab.net/blog/?p=772002024-05-07T19:14:23Z2024-02-01T21:00:00ZLarge language models (LLMs) have revolutionized the field of AI, creating entirely new ways of interacting with the digital world. While they provide a good...
]]>0Shashank Verma<![CDATA[Query Graphs with Optimized DePlot Model]]>http://www.open-lab.net/blog/?p=770032024-05-07T16:48:52Z2024-01-23T00:34:34ZNVIDIA AI Foundation Models and Endpoints provides access to a curated set of community and NVIDIA-built generative AI models to experience, customize, and...
]]>0Piotr ?elasko<![CDATA[New Support for Dutch and Persian Released by NVIDIA NeMo ASR]]>http://www.open-lab.net/blog/?p=766362024-02-08T18:52:04Z2024-01-16T18:29:16ZBreaking barriers in speech recognition, NVIDIA NeMo proudly presents pretrained models tailored for Dutch and Persian��languages often overlooked in the AI...
]]>1Pawe? Budzianowski<![CDATA[Enhancing Phone Customer Service with ASR Customization]]>http://www.open-lab.net/blog/?p=755842024-01-25T18:17:37Z2024-01-09T17:00:00ZAt the core of understanding people correctly and having natural conversations is automatic speech recognition (ASR). To make customer-led voice assistants and...
]]>0Annamalai Chockalingam<![CDATA[Contest: Build Generative AI on NVIDIA RTX PCs]]>http://www.open-lab.net/blog/?p=761412024-06-06T16:19:30Z2024-01-08T16:30:00ZNVIDIA is announcing the Generative AI on RTX PCs Developer Contest - designed to inspire innovation within the developer community. Build and submit your next...
]]>0Seth Schneider<![CDATA[Building Lifelike Digital Avatars with NVIDIA ACE Microservices]]>http://www.open-lab.net/blog/?p=761472024-01-25T18:17:41Z2024-01-08T16:30:00ZGenerative AI technologies are revolutionizing how games are produced and played. Game developers are exploring how these technologies can accelerate their...
]]>0Annamalai Chockalingam<![CDATA[Supercharging LLM Applications on Windows PCs with NVIDIA RTX Systems]]>http://www.open-lab.net/blog/?p=761742024-11-14T16:11:22Z2024-01-08T16:30:00ZLarge language models (LLMs) are fundamentally changing the way we interact with computers. These models are being incorporated into a wide range of...
]]>0Jesse Clayton<![CDATA[Get Started with Generative AI Development for Windows PCs with NVIDIA RTX]]>http://www.open-lab.net/blog/?p=762272024-11-14T16:14:11Z2024-01-08T16:30:00ZGenerative AI and large language models (LLMs) are changing human-computer interaction as we know it. Many use cases would benefit from running LLMs locally on...
]]>7Hayden Wolff<![CDATA[RAG 101: Retrieval-Augmented Generation Questions Answered]]>http://www.open-lab.net/blog/?p=757432024-11-20T23:02:36Z2023-12-18T19:44:42ZData scientists, AI engineers, MLOps engineers, and IT infrastructure professionals must consider a variety of factors when designing and deploying a RAG...
]]>2Hayden Wolff<![CDATA[RAG 101: Demystifying Retrieval-Augmented Generation Pipelines]]>http://www.open-lab.net/blog/?p=754932024-08-22T21:46:12Z2023-12-18T19:44:31ZLarge language models (LLMs) have impressed the world with their unprecedented capabilities to comprehend and generate human-like responses. Their chat...
]]>1Ike Nnoli<![CDATA[Create Lifelike Avatars with AI Animation and Speech Features in NVIDIA ACE]]>http://www.open-lab.net/blog/?p=741592024-11-20T23:02:47Z2023-12-04T22:00:00ZNVIDIA today unveiled major upgrades to the NVIDIA Avatar Cloud Engine (ACE) suite of technologies, bringing enhanced realism and accessibility to AI-powered...
]]>0Mohamed Elshenawy<![CDATA[Boost Meeting Productivity with AI-Powered Note-Taking and Summarization]]>http://www.open-lab.net/blog/?p=739642023-12-14T19:27:34Z2023-11-29T21:00:00ZMeetings are the lifeblood of an organization. They foster collaboration and informed decision-making. They eliminate silos through brainstorming and...