Student Researcher [Seed Vision – World Models for Video Generation] – 2026 Star

Overview

Student Researcher [Seed Vision – World Models for Video Generation] – 2026 Start (PhD) at ByteDance. PhD internships provide students with opportunities to contribute to products and research, with hands-on learning and collaboration with industry experts. Applications are reviewed on a rolling basis; please state your availability (start date and end date) in your resume.

Responsibilities

• Develop world models that simulate physical, embodied, or abstract environments through video generation.
• Learn latent dynamics from video sequences that support controllable or goal-conditioned generation.
• Model spatial-temporal consistency, causality, and state transitions in realistic or synthetic video datasets.
• Explore integration of control signals (e.g., actions, prompts, scene graphs) into video generation pipelines.
• Build benchmarks and analysis tools to measure dynamics understanding and causal consistency.

Qualifications

Minimum Qualifications:

• Currently pursuing a PhD in Computer Vision, Machine Learning, or a related field.
• Research experience in video generation, world models, or dynamics modeling.
• First-author publications in CVPR, ICCV, ECCV, NeurIPS, ICLR, or ICML.
• Familiarity with generative frameworks (e.g., VAE, diffusion, transformers) and temporal modeling.

Preferred Qualifications:

• Experience with model-based RL, embodied video prediction, or interactive generative agents.
• Understanding of structured representations (e.g., latent state, object-centric video models).
• Familiarity with datasets like Physion, CATER, or RLBench for grounded video modeling.

Job Information

Compensation: Hourly intern rate described as part of the campus intern program. Benefits vary by location; interns typically have access to health insurance, wellbeing benefits, and paid holidays/time off. Housing allowances may be available for non-remote roles in some cases. The Company reserves the right to modify benefits programs at any time.

Equal Opportunity & Accommodation
ByteDance is committed to diversity, inclusion, and providing reasonable accommodations in recruitment processes for candidates with disabilities or other protected reasons. If you need assistance or an accommodation, please contact us for accommodations requests.

Location notes and additional postings: Palo Alto, CA and Mountain View, CA appearances for related roles and salary ranges are listed separately per posting.