Xpeng

Overview

We are seeking PhD research interns with strong expertise in generative modeling and a demonstrated record of original research to develop world models that learn the dynamics of the physical world from large-scale multimodal data.

About Xpeng

XPENG is a leading smart technology company at the forefront of innovation, integrating advanced AI and autonomous driving technologies into its vehicles, including electric vehicles (EVs), electric vertical take-off and landing (eVTOL) aircraft, and robotics.

Requirements & Eligibility

• Currently pursuing a PhD in Engineering, Computer Science, or a related field, with a focus on Deep Learning, Computer Vision, or Generative Models.
• First-author publications at top-tier venues such as CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, CoRL, RSS, or SIGGRAPH.
• Strong, up-to-date foundation in generative modeling and experimental methodology, with hands-on experience building, training, fine-tuning, and evaluating models in PyTorch or JAX.
• Strong Python programming and software design skills, with a solid understanding of data structures, algorithms, code optimization, and large-scale data processing.
• Available to commit to a minimum of 12 weeks and work on-site at our Santa Clara office.

Key Responsibilities

• Drive a focused research project on predictive world models, spanning problem formulation, architecture design, training, evaluation, and empirical analysis, in close collaboration with a mentor and the broader research team.
• Contribute to one or more directions including high-quality multi-view future prediction and generation, predictive pre-training, and architectures in which a shared backbone predicts the future and produces trajectories or actions.
• Extend prediction beyond 2D pixels into a shared multimodal latent space that spans 3D scene representations such as Gaussian Splatting.
• Investigate cross-embodiment generalization through unified observation and action representations and embodiment-conditioning mechanisms.
• Build evaluation methodology for predictive world models spanning representation quality, prediction accuracy, generation fidelity, and physical plausibility.
• Collaborate with research engineers to move research prototypes into scalable training and inference pipelines.