Research Intern – World-Action Model / VLA for Autonomous Driving
Core
Designing and training world-action models (autoregressive/diffusion-based) and integrating them with planning for end-to-end or model-based driving policies in autonomous driving.
Role type
Research Intern (Ph.D. student)
Builds
Scalable autonomy research, world models, and driving policies
Domain
Autonomous Driving / ADAS / Generative AI
Deliverable
research
Required skills
generative models (diffusion, autoregressive transformers, VAEs), world models / video prediction, deep learning frameworks, reinforcement learning, model-based planning
Preferred skills
publication record in top venues (CVPR, ICCV, ECCV, ICLR, NeurIPS, ICML), familiarity with driving benchmarks (NavSim, Bench2Drive), large-scale distributed training, multi-modal/video data pipelines
Technologies
diffusion models, autoregressive transformers, VAEs, deep learning frameworks
Responsibilities
Designing and training world-action models, integrating world models with planning, summarizing research findings in papers or patents
Seniority
Intern (Ph.D. student)