[Remote] Student Researcher [Seed Vision – World Models for Video Generation] – 2026 Start (PhD)

Note: The job is a remote job and is open to candidates in USA. ByteDance is a leading technology company committed to pioneering advanced AI foundation models. The Student Researcher will contribute to foundational models for visual generation, focusing on developing multimodal generative models and addressing fundamental computer vision challenges.

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

Skills

• 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
• 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

Benefits

• Day one access to health insurance
• Life insurance
• Wellbeing benefits
• 10 paid holidays per year
• Paid sick time (56 hours if hired in first half of year, 40 if hired in second half of year)
• Housing allowance

Company Overview

Company H1B Sponsorship