This session is worth the wait.
We’re getting the recording ready. Check back soon to watch the full session.

Scaling the Data Foundation for XPENG's VLA 2.0

Autonomous Driving

Model Training

Data Curation

Bo Tian explains how XPENG uses Lance for direct training reads, evolving datasets, and mining rare driving scenarios for VLA 2.0.

Scaling the Data Foundation for XPENG's VLA 2.0

Scaling the Data Foundation for XPENG's VLA 2.0

Autonomous Driving

Model Training

Data Curation

Bo Tian explains how XPENG uses Lance for direct training reads, evolving datasets, and mining rare driving scenarios for VLA 2.0.

Thank you! Your recording is ready.

Your submission was successful. The video will appear in a moment.

Bo Tian
Principal Machine Learning Engineer
XPeng

About This Talk

XPENG's VLA 2.0 (Vision-Language-Action) system learns to drive from an enormous, constantly growing corpus of multimodal data, including multi-camera video, sensor streams, and the language annotations that tie perception to action.

In this talk, Bo Tian will share how XPENG rebuilt its data infrastructure to serve as the foundation for VLA 2.0 training. The session will cover three shifts. First, training reads directly from Lance datasets on object storage, with random access fast enough that to no longer need to stage data onto a parallel file system before each job. Second, Lance's versioning and schema evolution to let annotation, curation, and feature teams add columns and iterate on datasets without rewriting the underlying video, so data iteration keeps pace with model iteration. Third, Lance's built-in vector search supports data mining, with embeddings alongside the raw clips, so engineers can find rare and long-tail scenarios with similarity queries across billion-scale clips and feed them straight into training sets.

The talk will close with lessons learned from running Lance at production scale in an autonomous-driving setting, and how XPENG sees the format evolving for embodied AI and robotics workloads.

About The Speaker

Bo Tian

Bo Tian leads the ML infrastructure team behind its autonomous driving and robotics work. His team owns the full stack: data ingestion, mining, and training pipelines; training framework and acceleration; the LLM inference platform; and closed-loop simulation. He designs data, training, and inference as one pipeline so gains in each layer compound.

Transcript

Show transcriptHide transcript

Related recordings

Cosmos: Omnimodal World Models for Physical AI

Max Li
•
Session
cosmos-omnimodal-world-models-for-physical-ai

Physical AI

Multimodal Data

Model Training

Scalable, Multimodal Data Curation

Ethan Rosenthal
•
Session
scalable-multimodal-data-curation

Data Curation

Multimodal Data

Search & Retrieval

Building the Data Flywheel for Frontier AI Model

Suqiang (Jack) Song
•
Session
building-the-data-flywheel-for-frontier-ai-model

Data Curation

Model Training

Multimodal Data

From Raw Driving Logs to RL Training: A Petabyte-Scale Lance Pipeline in Production

Shiyan Xu
•
Session
from-raw-driving-logs-to-rl-training-a-petabyte-scale-lance-pipeline-in-production

Autonomous Driving

Data Curation

Model Training

From Raw Delivery to the Training Loop: Luma's Data Platform on Lance

Haoran Cai
•
Session
from-raw-delivery-to-the-training-loop-luma-s-data-platform-on-lance

Multimodal Data

Data Curation

Model Training

Data Infrastructure for Robotics Foundation Models

Zhipeng Yan
•
Session
data-infrastructure-for-robotics-foundation-models

Physical AI

AI Infrastructure

Model Training

What Does "Now" Mean to Your Model? Time Alignment for Multimodal AI Data

Vasundra Srinivasan
•
Session
what-does-now-mean-to-your-model

Multimodal Data

Physical AI

Model Training

Scaling the Data Foundation for XPENG's VLA 2.0

Bo Tian
•
Session
scaling-the-data-foundation-for-xpengs-vla-2-0

Autonomous Driving

Model Training

Data Curation

Keynote | Rethinking AI Infrastructure

Gerred Dillon
•
Keynote
rethinking-ai-infrastructure

AI Infrastructure

Model Training