The next DLSS feature: ray reconstruction. Joint denoising and superresolution for raytracing. Solving these problems jointly makes games more detailed and dynamic, on all RTX GPUs. DLSS just keeps learning. youtu.be/sGKCrcNsVzo

This was perhaps the most eye-popping tech thing I saw at Gamescom. I have spent the last 5 years appreciating real-time denoisers for RT, and DLSS 3.5 ray reconstruction kind of makes all preceeding ones obsolete in every visible problem area I am used to seeing. Ridiculous tech

So fulfilling to see such well done reviews that highlight both our triumphs and challenges together like Digital Foundry's latest: youtu.be/hhAtN_rRuQo. Thank you for always setting such a high bar Alexander Battaglia and team.

Jensen Huang is an intensely driven visionary. Working at NVIDIA is exciting and fast paced because he sets the tone. I think his story should be more widely known - in my mind he is just as much a tech titan as Steve Jobs, Bill Gates, or Mark Zuckerberg. newyorker.com/magazine/2023/…

ChatQA can outperform GPT-4 on a wide range of conversational QA tasks: - ChatQA and GPT-4 take the same top-5 chunks from our best retriever, when long documents are involved. - ChatQA performs very well on tabular data, arithmetic calculation, and “unanswerable” cases!

NVIDIA’s Applied Deep Learning Research is hiring! Come join us if you want to dive into projects like DLSS and push the boundaries of graphics and gaming with AI. Feel free to DM me. nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAEx…

🚀Introducing Nemotron-4 15B by NVIDIA! 🎉 With 15B parameters and trained on 8T tokens, it's impressive in multilingual AI. Outperforms all similarly-sized models and dominates in multilingual tasks, even surpassing models 4x larger! #NVIDIA #Nemotron4 arxiv.org/pdf/2402.16819…

Not everyone knows, but Nvidia is training world class LLMs. arxiv.org/abs/2402.16819. And there’s more to come

@luka_emon When I started, I didn't understand where the problems lie with AMD. I thought it was the driver, it's not. tinygrad is now submitting AQL queues directly to the GPU. It's the firmware, and it might even be the hardware. NVDA deserves to be king.

Finally, a shout-out to our wonderful Eagle Team and all the collaborators! Min Shi Fuxiao Liu Shihao Wang Guilin Liu Subhashree Radhakrishnan De-An Huang Hongxu (Danny) Yin Karan Sapra Yaser Yacoob Humphrey Shi Bryan Catanzaro Andrew Tao Jan Kautz

We are very excited to release our Common Crawl based large scale dataset. This 6.3T tokens dataset will help the community develop stronger models. Check it out!

Introducing NVIDIA DLSS 4 featuring new Multi Frame Generation and everything enhanced ⚡ Supreme Speed. Superior Visuals. Powered by AI. Learn more → nvda.ws/40o9I4E

Today on Digital Foundry, Alexander Battaglia spends some time talking machine learning, DLSS and more with Nvidia's Bryan Catanzaro - Bryan Catanzaro: youtu.be/uyxXRXDtcPA

Nvidia’s OCR solution (maths and tables also extracted): build.nvidia.com/nvidia/nemoret… based on arxiv.org/abs/2502.04223

Extremely proud of the team’s work to make DLSS4 a reality, where team == SW, Devtech, Product, Research … We’re on a mission to reinvent graphics with deep learning and genAI. Come work with us! research.nvidia.com/labs/adlr/DLSS… edliu1105 Bryan Catanzaro

A long time ago, back before DLSS was in many games (and when my hair was shorter and less gray), I went to Nintendo HQ to show them an early prototype of DLSS 2, in the hopes that a future Switch console would use DLSS. I'm so proud that the Switch 2 will be DLSS powered!

Vision Language Models can be amazing at document understanding. Please check out our Nano sized model. More to come!