News from the AI & ML world
DeeperML
@the-decoder.com
//
Nvidia is making significant advancements in artificial intelligence, showcasing innovations in both hardware and video generation. A new method developed by Nvidia, in collaboration with Stanford University, UCSD, UC Berkeley, and UT Austin, allows for the creation of AI-generated videos up to one minute long. This breakthrough addresses previous limitations in video length, where models like OpenAI's Sora, Meta's MovieGen, and Google's Veo 2 were capped at 20, 16, and 8 seconds respectively.
The key innovation lies in the introduction of Test-Time Training layers (TTT layers), which are integrated into a pre-trained Transformer architecture. These layers replace simple hidden states in conventional Recurrent Neural Networks (RNNs) with small neural networks that continuously learn during the video generation process. This allows the system to maintain consistency across longer sequences, ensuring elements like characters and environments remain stable throughout the video. This new method has even been showcased with an AI-generated "Tom and Jerry" cartoon.
Furthermore, Nvidia has unveiled its new Llama-3.1 Nemotron Ultra large language model (LLM), which outperforms DeepSeek R1 despite having less than half the parameters. The Llama-3.1-Nemotron-Ultra-253B is a 253-billion parameter model designed for advanced reasoning, instruction following, and AI assistant workflows. Its architecture includes innovations such as skipped attention layers, fused feedforward networks, and variable FFN compression ratios. The model's code is publicly available on Hugging Face, reflecting Nvidia's commitment to open-source AI development.
ImgSrc: the-decoder.com
References :
The key innovation lies in the introduction of Test-Time Training layers (TTT layers), which are integrated into a pre-trained Transformer architecture. These layers replace simple hidden states in conventional Recurrent Neural Networks (RNNs) with small neural networks that continuously learn during the video generation process. This allows the system to maintain consistency across longer sequences, ensuring elements like characters and environments remain stable throughout the video. This new method has even been showcased with an AI-generated "Tom and Jerry" cartoon.
Furthermore, Nvidia has unveiled its new Llama-3.1 Nemotron Ultra large language model (LLM), which outperforms DeepSeek R1 despite having less than half the parameters. The Llama-3.1-Nemotron-Ultra-253B is a 253-billion parameter model designed for advanced reasoning, instruction following, and AI assistant workflows. Its architecture includes innovations such as skipped attention layers, fused feedforward networks, and variable FFN compression ratios. The model's code is publicly available on Hugging Face, reflecting Nvidia's commitment to open-source AI development.
ImgSrc: the-decoder.com
Share:
References :
- analyticsindiamag.com: NVIDIA-Backed Rescale secures $115 Mn in Series D Round
- the-decoder.com: AI-generated Tom chases Jerry for a full minute thanks to new method from Nvidia and others
- AI News | VentureBeat: Nvidia’s new Llama-3.1 Nemotron Ultra outperforms DeepSeek R1 at half the size
- THE DECODER: AI-generated Tom chases Jerry for a full minute thanks to new method from Nvidia and others
Classification:
- HashTags: #NvidiaAI #AIHardware #AIVideoGeneration
- Company: Nvidia
- Target: AI Community, Researchers
- Product: Nemotron Ultra, Llama-3.1
- Feature: AI video generation
- Type: AI
- Severity: Informative