Speaker: Harpreet Sahota, Hacker-in-Residence at Voxel51

Live, expert-led sessions where you’ll build real agentic systems step-by-step.

Modern mobility systems rely on massive, high-quality multimodal datasets — yet real-world data is messy. Misaligned sensors, inconsistent metadata, and uneven scenario coverage can slow development and lead to costly model failures. The Physical AI Workbench, built in collaboration between Voxel51 and NVIDIA, provides an automated and scalable pipeline for auditing, reconstructing, and enriching autonomous driving datasets.

In this talk, we’ll show how FiftyOne serves as the central interface for inspecting and validating sensor alignment, scene structure, and scenario diversity, while NVIDIA Neural Reconstruction (NuRec) enables physics-aware reconstruction directly from real-world captures. We’ll highlight how these capabilities support automated dataset quality checks, reduce manual review overhead, and streamline the creation of richer datasets for model training and evaluation.

Attendees will gain insight into how Physical AI workflows help mobility teams scale, improve dataset reliability, and accelerate iteration from data capture to model deployment — without rewriting their infrastructure.

Modern mobility systems rely on massive, high-quality multimodal datasets — yet real-world data is messy. Misaligned sensors, inconsistent metadata, and uneven scenario coverage can slow development and lead to costly model failures. The Physical AI Workbench, built in collaboration between Voxel51 and NVIDIA, provides an automated and scalable pipeline for auditing, reconstructing, and enriching autonomous driving datasets. In this talk, we’ll show how FiftyOne serves as the central interface for inspecting and validating sensor alignment, scene structure, and scenario diversity, while NVIDIA Neural Reconstruction (NuRec) enables physics-aware reconstruction directly from real-world captures. We’ll highlight how these capabilities support automated dataset quality checks, reduce manual review overhead, and streamline the creation of richer datasets for model training and evaluation. Attendees will gain insight into how Physical AI workflows help mobility teams scale, improve dataset reliability, and accelerate iteration from data capture to model deployment — without rewriting their infrastructure.

Modern mobility systems rely on massive, high-quality multimodal datasets — yet real-world data is messy. Misaligned sensors, inconsistent metadata, and uneven scenario coverage can slow development and lead to costly model failures. The Physical AI Workbench, built in collaboration between Voxel51 and NVIDIA, provides an automated and scalable pipeline for auditing, reconstructing, and enriching autonomous driving datasets. In this talk, we’ll show how FiftyOne serves as the central interface for inspecting and validating sensor alignment, scene structure, and scenario diversity, while NVIDIA Neural Reconstruction (NuRec) enables physics-aware reconstruction directly from real-world captures. We’ll highlight how these capabilities support automated dataset quality checks, reduce manual review overhead, and streamline the creation of richer datasets for model training and evaluation. Attendees will gain insight into how Physical AI workflows help mobility teams scale, improve dataset reliability, and accelerate iteration from data capture to model deployment — without rewriting their infrastructure.

Modern mobility systems rely on massive, high-quality multimodal datasets — yet real-world data is messy. Misaligned sensors, inconsistent metadata, and uneven scenario coverage can slow development and lead to costly model failures. The Physical AI Workbench, built in collaboration between Voxel51 and NVIDIA, provides an automated and scalable pipeline for auditing, reconstructing, and enriching autonomous driving datasets. In this talk, we’ll show how FiftyOne serves as the central interface for inspecting and validating sensor alignment, scene structure, and scenario diversity, while NVIDIA Neural Reconstruction (NuRec) enables physics-aware reconstruction directly from real-world captures. We’ll highlight how these capabilities support automated dataset quality checks, reduce manual review overhead, and streamline the creation of richer datasets for model training and evaluation. Attendees will gain insight into how Physical AI workflows help mobility teams scale, improve dataset reliability, and accelerate iteration from data capture to model deployment — without rewriting their infrastructure.

Modern mobility systems rely on massive, high-quality multimodal datasets — yet real-world data is messy. Misaligned sensors, inconsistent metadata, and uneven scenario coverage can slow development and lead to costly model failures. The Physical AI Workbench, built in collaboration between Voxel51 and NVIDIA, provides an automated and scalable pipeline for auditing, reconstructing, and enriching autonomous driving datasets.\n\nIn this talk, we’ll show how FiftyOne serves as the central interface for inspecting and validating sensor alignment, scene structure, and scenario diversity, while NVIDIA Neural Reconstruction (NuRec) enables physics-aware reconstruction directly from real-world captures. We’ll highlight how these capabilities support automated dataset quality checks, reduce manual review overhead, and streamline the creation of richer datasets for model training and evaluation.\n\nAttendees will gain insight into how Physical AI workflows help mobility teams scale, improve dataset reliability, and accelerate iteration from data capture to model deployment — without rewriting their infrastructure.

Modern mobility systems rely on massive, high-quality multimodal datasets — yet real-world data is messy. Misaligned sensors, inconsistent metadata, and uneven scenario coverage can slow development and lead to costly model failures. The Physical AI Workbench, built in collaboration between Voxel51 and NVIDIA, provides an automated and scalable pipeline for auditing, reconstructing, and enriching autonomous driving datasets. In this talk, we’ll show how FiftyOne serves as the central interface for inspecting and validating sensor alignment, scene structure, and scenario diversity, while NVIDIA Neural Reconstruction (NuRec) enables physics-aware reconstruction directly from real-world captures. We’ll highlight how these capabilities support automated dataset quality checks, reduce manual review overhead, and streamline the creation of richer datasets for model training and evaluation. Attendees will gain insight into how Physical AI workflows help mobility teams scale, improve dataset reliability, and accelerate iteration from data capture to model deployment — without rewriting their infrastructure.

Modern mobility systems rely on massive, high-quality multimodal datasets — yet real-world data is messy. Misaligned sensors, inconsistent metadata, and uneven scenario coverage can slow development and lead to costly model failures. The Physical AI Workbench, built in collaboration between Voxel51 and NVIDIA, provides an automated and scalable pipeline for auditing, reconstructing, and enriching autonomous driving datasets.\n\nIn this talk, we’ll show how FiftyOne serves as the central interface for inspecting and validating sensor alignment, scene structure, and scenario diversity, while NVIDIA Neural Reconstruction (NuRec) enables physics-aware reconstruction directly from real-world captures. We’ll highlight how these capabilities support automated dataset quality checks, reduce manual review overhead, and streamline the creation of richer datasets for model training and evaluation.\n\nAttendees will gain insight into how Physical AI workflows help mobility teams scale, improve dataset reliability, and accelerate iteration from data capture to model deployment — without rewriting their infrastructure.

Paula Ramos, PhD is a Senior Developer Relations Specialist at Voxel51. She specializes in helping developers implement effective computer vision solutions for autonomous systems and building a community around open-source computer vision tools.

In this talk, we’ll explore Janus-Pro’s Visual Question Answer (VQA) capabilities using FiftyOne’s Janus-Pro VQA Plugin. The plugin provides a seamless interface to Janus Pro’s visual question understanding capabilities within FiftyOne, offering: Vision-language tasks; Hardware acceleration (CUDA/MPS) when available; Dynamic version selection from HuggingFace; Full integration with FiftyOne’s Dataset and UI.

DeepSeek’s Janus-Pro is an advanced multimodal model designed for both multimodal understanding and visual generation, with a particular emphasis on improvements in understanding tasks. In this talk, we’ll explore Janus-Pro’s Visual Question Answer (VQA) capabilities using FiftyOne’s Janus-Pro VQA Plugin. The plugin provides a seamless interface to Janus Pro’s visual question understanding capabilities within FiftyOne, offering: Vision-language tasks; Hardware acceleration (CUDA/MPS) when available; Dynamic version selection from HuggingFace; Full integration with FiftyOne’s Dataset and UI. Can’t wait to see it for yourself? Check out the FiftyOne Quickstart with Janus-Pro.

Exploration of Janus-Pro’s VQA capabilities using FiftyOne’s Janus-Pro VQA Plugin, with a focus on vision-language tasks, hardware acceleration (CUDA/MPS), dynamic version selection from HuggingFace, and full integration with FiftyOne’s Dataset and UI.

Join us for a quick update on the Elderly Action Recognition (EAR) Challenge, part of the Computer Vision for Smalls (CV4Smalls) Workshop at the WACV 2025 conference! This challenge focuses on advancing research in Activity of Daily Living (ADL) recognition, particularly within the elderly population, a domain with profound societal implications. Participants will employ transfer learning techniques with any architecture or model they want to use.

Join us for a quick update on the Elderly Action Recognition (EAR) Challenge, part of the Computer Vision for Smalls (CV4Smalls) Workshop at the WACV 2025 conference! This challenge focuses on advancing research in Activity of Daily Living (ADL) recognition, particularly within the elderly population, a domain with profound societal implications. Participants will employ transfer learning techniques with any architecture or model they want to use. For example, starting with a general human action recognition benchmark and fine-tuning models on a subset of data tailored to elderly-specific activities.

Join us for a quick update on the Elderly Action Recognition (EAR) Challenge, part of the Computer Vision for Smalls (CV4Smalls) Workshop at the WACV 2025 conference! This challenge focuses on advancing research in Activity of Daily Living (ADL) recognition, particularly within the elderly population, a domain with profound societal implications. Participants will employ transfer learning techniques with any architecture or model they want to use. For example, starting with a general human action recognition benchmark and fine-tuning models on a subset of data tailored to elderly-specific activities. Sign up for the EAR challenge and learn more.

Hands-on 90-minute workshop to learn how to leverage the FiftyOne computer vision toolset. Part 1 covers FiftyOne basics (terms, architecture, installation, and general usage), an overview of useful workflows to explore, understand, and curate data, and how FiftyOne represents and semantically slices unstructured computer vision data. Part 2 is a hands-on introduction to FiftyOne, where you will learn how to load datasets from the FiftyOne Dataset Zoo, navigate the FiftyOne App, programmatically inspect attributes of a dataset, add new sample and custom attributes to a dataset, generate and evaluate model predictions, and save insightful views into the data. Prerequisites: working knowledge of Python and basic computer vision. Attendees will get access to tutorials, videos, and code examples used in the workshop.

90-minute hands-on workshop led by Harpreet Sahota, Hacker-in-Residence and Machine Learning Engineer at Voxel51. Part 1 covers FiftyOne basics (terms, architecture, installation, general usage), an overview of useful workflows to explore, understand, and curate data, and how FiftyOne represents and semantically slices unstructured computer vision data. Part 2 provides a hands-on introduction to FiftyOne: loading datasets from the FiftyOne Dataset Zoo, navigating the FiftyOne App, programmatically inspecting attributes, adding new samples and custom attributes, generating and evaluating model predictions, and saving insightful views into the data. Prerequisites: working knowledge of Python.

An introduction to FiftyOne basics (terms, architecture, installation, and general usage), overview of workflows to explore, understand, and curate data, and how FiftyOne represents and semantically slices unstructured computer vision data.

Hands-on introduction to FiftyOne: load datasets from the FiftyOne Dataset Zoo, navigate the FiftyOne App, programmatically inspect attributes of a dataset, add new samples and custom attributes, generate and evaluate model predictions, and save insightful views into the data.

A 90-minute hands-on workshop introducing the FiftyOne computer vision toolset. Part 1 covers FiftyOne basics (terms, architecture, installation, and general usage), an overview of useful workflows to explore, understand, and curate data, and how FiftyOne represents and semantically slices unstructured computer vision data. Part 2 is a hands-on session on loading datasets from the FiftyOne Dataset Zoo, navigating the FiftyOne App, programmatically inspecting attributes of a dataset, adding new samples and custom attributes, generating and evaluating model predictions, and saving insightful views into the data.

90-minute hands-on workshop on the FiftyOne computer vision toolset. Part 1 covers FiftyOne Basics (terms, architecture, installation, and general usage); an overview of useful workflows to explore, understand, and curate data; and how FiftyOne represents and semantically slices unstructured computer vision data. Part 2 provides a hands-on introduction to FiftyOne: loading datasets from the FiftyOne Dataset Zoo, navigating the FiftyOne App, programmatically inspecting dataset attributes, adding new samples and custom attributes, generating and evaluating model predictions, and saving insightful views into the data. Prerequisites: working knowledge of Python. All attendees get access to tutorials, videos, and code examples used in the workshop.

Overview of FiftyOne basics (terms, architecture, installation, and general usage). An overview of useful workflows to explore, understand, and curate your data. How FiftyOne represents and semantically slices unstructured computer vision data.

Overview of FiftyOne basics: terms, architecture, installation, and general usage; an overview of useful workflows to explore, understand, and curate your data; and how FiftyOne represents and semantically slices unstructured computer vision data.

90-minute hands-on workshop on the FiftyOne computer vision toolset. Part 1 covers FiftyOne basics (terms, architecture, installation, and general usage), an overview of useful workflows to explore, understand, and curate data, and how FiftyOne represents and semantically slices unstructured computer vision data. Part 2 is a hands-on introduction to FiftyOne: loading datasets from the FiftyOne Dataset Zoo, navigating the FiftyOne App, programmatically inspecting attributes, adding new samples and custom attributes, generating and evaluating model predictions, and saving insightful views into the data.