Autonomous driving

Models 9

• Gen 3
  Cosmos3-Edge

  By NVIDIA

  Cosmos3-Edge is a 4 billion parameter open world model built to run on-device. It helps robots and vision AI agents understand their surroundings, reason in real time, and generate robot actions on edge hardware such as NVIDIA Jetson and RTX GPUs. It combines an autoregressive reasoning tower with a diffusion generation tower to unify scene understanding, video prediction, and action generation.

  🤖Robotics📽️Image to video🎥Videos🚗Autonomous driving
  NewMultimodal

  Released 1d ago
• Research previewGen 1 Qwen
  Qwen-RobotWorld

  By Alibaba

  Language-conditioned video world model for embodied AI that predicts physically grounded future visual trajectories from natural language instructions and current observations. Supports robotic manipulation, autonomous driving, indoor navigation, and human-to-robot transfer. Built on a 60-layer double-stream diffusion transformer coupled with Qwen2.5-VL semantics.

  🎥Video generation🤖Robotics🚗Autonomous driving
  NewVideo

  Released 1mo ago
• AnnouncementGen 3
  NVIDIA Alpamayo 2 Super

  By NVIDIA

  A 32-billion-parameter open reasoning-based vision language action (VLA) model for level 4 autonomous vehicle development. Processes 360-degree multi-camera input to enable perception, reasoning, and trajectory planning across the full driving stack. Outputs chain-of-causation traces, Meta-Actions, and trajectory predictions.

  🤖Robotics🏷️Data labeling👁️Computer vision assistance🚗Autonomous driving
  NewMultimodal

  Released 1mo ago
• Gen 3 MiniMax
  NVIDIA Cosmos 3

  By NVIDIA

  Cosmos 3 is NVIDIA’s open physical-AI foundation model for vision reasoning, world simulation, multimodal generation, and action prediction.

  🎮Interactive simulation🔀Synthetic data🤖Robotics🚗Autonomous driving
  NewMultimodal

  Released 1mo ago
• Gen 3
  Asset Harvester

  By NVIDIA

  Asset Harvester is NVIDIA’s open framework for extracting reusable 3D assets from sparse autonomous-driving observations. It turns one or a few in-the-wild object views from driving logs into complete, simulation-ready 3D assets, even under occlusion, noisy calibration, and viewpoint bias.

  🎲3D objects🎥3D scenes🚗Autonomous driving
  Multimodal

  Released 3mo ago
• Gen 3
  Alpamayo 1.5 10B

  By NVIDIA

  Alpamayo 1.5-10B is NVIDIA’s open 10B vision-language-action model for autonomous driving. It is built as a steerable reasoning engine for AV research, combining multi-camera visual input, text, and egomotion history to produce both chain-of-causation reasoning and future driving trajectories.

  🚗Autonomous driving🔍Advanced reasoning🔍Image interpretation👁️Computer vision assistance
  Multimodal

  Released 4mo ago
• Gen 3
  FlashDrive

  By Z Lab

  FlashDrive is Z Lab’s real-time inference framework for vision-language-action autonomous driving models. It is designed to make reasoning-based end-to-end driving practical by accelerating all major inference stages, reducing latency from 716 ms to 159 ms on Alpamayo 1.5 while keeping accuracy nearly unchanged.

  🧠AI inference🗃️Model utilization🚗Autonomous driving
  Multimodal

  Released 4mo ago
• Gen 7
  Alpamayo R1

  By NVIDIA

  Alpamayo-R1 is NVIDIA's vision-language-action model for autonomous driving, combining Chain of Causation reasoning with trajectory planning to handle long-tail, safety-critical situations more robustly and with interpretable decisions.

  🚗Autonomous driving🔍SEO content💼LinkedIn messages
  Text

  Released 8mo ago
• Gen 3
  Cosmos Reason

  By NVIDIA

  Cosmos Reason is NVIDIA’s open, customizable 7B-parameter reasoning VLM for physical AI and robotics. It learns space/time/physics “common sense,” plans actions from video/images, and was trained with SFT + RL. Available under the NVIDIA Open Model License on GitHub/Hugging Face and as an NVIDIA NIM.

  🚗Autonomous driving🍔Burger images🤖Cybernetic art
  Text

  Released 10mo ago