Student Researcher (Multimodal Interaction and World Model - Seed) – 2027 Start (PhD)

About the team
The Seed Multimodal Interaction and World Model team is dedicated to developing models that have human-level multimodal understanding and interaction capabilities. The team is working to advance the exploration and development of multimodal assistant products.

Responsibilities:

• Conduct research on multimodal foundation models and related systems.
• Explore methods to improve model capabilities across modalities, including areas such as vision-language modeling, world modeling, and representation learning.
• Design and prototype algorithms, models, or system components.
• Collaborate with the team to advance research directions.

Requirements:

• Minimum Qualifications

• Currently pursuing a PhD in computer science, mathematics, engineering, or a related field.

• Strong programming skills and solid foundation in algorithms and data structures, proficient in Python or C/C++.

• Demonstrated research track record with publications in conferences related to multimodal learning, machine learning, or artificial intelligence.

• Preferred Qualifications

• Experience in multimodal modeling, vision-language modeling, world modeling, simulation, or 3D representations. Experience with latent space modeling or structured representations is a plus.

• Strong problem-solving ability and experience conducting independent research.

• Ability to collaborate effectively in a research environment.