xtreme1-io/xtreme1
Multimodal training data platform for 3D LiDAR and images
View on index · View in 3D Map
Related repos
- Toolkit for fine-tuning and training large language and vision models
- Multimodal system for streaming video and audio interactions
- Unified model for photogrammetry subtasks
- Generates maps and 3D models from drone imagery
- library for training large models across any modality, config-driven and modular, from Apple Research
- multimodal AI model for text, image, and video tasks
- Skywork R1V: multimodal reasoning model extending R1-series LLMs to images and text, open-source, efficient transfer, 38B parameters
- MLX: array framework for machine learning on Apple silicon
- LiDAR SLAM at 400 FPS on KITTI
- Declarative infrastructure for storing and processing multimodal AI data with Python
