Controllable Video Generation Research Intern 108305
Core
Design a multimodal controllable generation framework for video generation supporting various inputs like keyboard, controller, trajectory, and voice to enable low-latency, multi-player collaborative control in games.
Role type
Research Intern (AI/Computer Vision)
Builds
Controllable video generation frameworks and dedicated control modules for game genres
Domain
Gaming, Computer Vision, Deep Learning
Deliverable
production ML models
Required skills
conditional generation models, diffusion models, trajectory control, camera control, motion control, posture control, Python, PyTorch
Preferred skills
Game AI, game development, real-time/interactive video generation
Technologies
PyTorch, Python
Responsibilities
Design multimodal controllable generation frameworks; research high-fidelity generation under sparse control signals; decouple and combine trajectory, camera, motion, and posture controls; develop video generation capabilities for multi-player collaborative control; collaborate on standardized interfaces for controllable signals; drive joint optimization with Reinforcement Learning post-training.
Seniority
Intern
