




Featured
From Fleet Log to Simulation-Ready Scenario: The Data Layer Behind an AV Data Flywheel
Read articleVoxel51 blog
Physical AI
Physical AI is AI that perceives and acts in the physical world: robots, autonomous vehicles, and drones. Posts cover curating and evaluating sensor data in FiftyOne, from MCAP logs to VLA policies.

by Harpreet Sahota, DevRel
Physical AI
• 
by Jesse Mostipak, Marketing
Physical AI
• 
by Layla Yun, Marketing
Physical AI
• Visual AI
Visual AI is how machines learn to see: detection, segmentation, embeddings, and vision-language models. These posts show how to debug, compare, and improve visual AI models with FiftyOne.
Search
Search is how you find what matters in datasets too large to review by hand. FiftyOne makes visual data searchable by natural language, similarity, and metadata to surface edge cases and rare scenarios.
Data curation
Data curation is choosing what to train on: surfacing edge cases, removing duplicates and leaky splits, and closing coverage gaps. These posts show how to do it at scale in FiftyOne.
Data annotation
Label quality caps model performance. These posts cover auto-labeling with foundation models, agentic labeling with the Voxel51 Agent, and finding label errors before they reach training.

by Jacob Sela, Machine Learning
Data annotation
• 
by Adonai Vera, DevRel
Data annotation, Product and news
• 
by Eric Hofesmann, Machine Learning
Data annotation, Product and news
• Model evaluation
A single accuracy number hides more than it reveals. Slice performance by class and scenario, analyze failure modes, and compare detection, segmentation, and VLM models side by side in FiftyOne.

by Adonai Vera, DevRel
Model evaluation
• 
by Harpreet Sahota, DevRel
Model evaluation
• 
by Jimmy Guerrero, Leadership
Model evaluation
• Datasets
Every model is a portrait of its dataset. We load open datasets like COCO, LIBERO, and Open X-Embodiment into FiftyOne to reveal the imbalances, errors, and hidden gems summary stats miss.
Plugins
Plugins make FiftyOne fully extensible. Build custom panels, operators, and workflows, or connect annotation tools, vector databases, and model APIs. If FiftyOne doesn't do it yet, a plugin probably can.

by Harpreet Sahota, DevRel
Physical AI
• 
Product and news
What's new at Voxel51: FiftyOne open source and Voxel51 releases, partnerships, ML research, and events like CVPR. Start here to see where the platform for physical AI is headed.

by Brian Moore, Leadership
Product and news, Physical AI
• 
by Dan Gural, DevRel
Product and news, Physical AI
• 
by Brian Moore, Leadership
Product and news, Physical AI
• All posts

by Harpreet Sahota, DevRel
Physical AI
• 
by Jesse Mostipak, Marketing
Physical AI
• 
by Layla Yun, Marketing
Physical AI
• 
by Mohamad Louai Shehab, Guest author
Physical AI
• 
by Mohamad Louai Shehab, Guest author
Physical AI
• 

by Jacob Sela, Machine Learning
Data annotation
• 

by Shaunak Roy, Graduate Student, University of Michigan Robotics
Physical AI
• 
by Brian Moore, Leadership
Product and news, Physical AI
• 
by Dan Gural, DevRel
Product and news, Physical AI
• 
by Brian Moore, Leadership
Product and news, Physical AI
• 











