About this opportunity
Opportunity Overview
Tencent is hiring a Controllable Video Generation Researcher to design a multimodal controllable generation framework. The researcher will work on high-fidelity generation under sparse control signals and explore the extension of conditional control paradigms in the video domain. The goal is to achieve the decoupling and combination of trajectory control, camera control, motion control, and posture control. The researcher will also develop video generation capabilities for multi-player collaborative control. The ideal candidate will have a Ph.D. in AI-related fields, focusing on Computer Vision/Deep Learning, and be proficient in conditional generation models and multi-player/multi-channel control technologies. The researcher will collaborate with the Engine/Agent teams to define standardized interfaces for controllable signals and drive the joint optimization of controllable generation and Reinforcement Learning post-training. Tencent values diversity and believes that diverse voices fuel innovation, allowing the company to better serve its users and the community. The company fosters an environment where every employee feels supported and inspired to achieve individual and common goals.
Responsibilities
- Design a multimodal controllable generation framework supporting various inputs such as keyboard, controller, trajectory, and voice
- Research high-fidelity generation under sparse control signals
- Explore the extension of conditional control paradigms in the video domain
- Achieve the decoupling and combination of trajectory control, camera control, motion control, and posture control
- Design dedicated control modules tailored to different game genres
- Develop video generation capabilities for multi-player collaborative control
- Collaborate with the Engine/Agent teams to define standardized interfaces for controllable signals
- Drive the joint optimization of controllable generation and Reinforcement Learning post-training
Requirements & Qualifications
- Ph.D. in AI-related fields, focusing on Computer Vision/Deep Learning
- Proficient in conditional generation models and multi-player/multi-channel control technologies
- Familiar with the principles of diffusion models
- Project experience in camera control, trajectory control, or posture control
- Understanding of game engine input/output logic and frame synchronization mechanisms
- Proficient in Python/PyTorch
- Publications in controllable video generation or conditional generation
- Experience in Game AI or game development is preferred
- Experience in real-time/interactive video generation projects is preferred
How to Apply
- Review the job description and requirements to ensure you are a good fit for the role.
- Prepare your application materials, including your resume and any relevant publications or project experience.
- Click the Apply button below to submit your application.
Ready to apply?