Responsibilities
1. Responsible for the exploration and research of cutting-edge technologies related to digital human video generation and driving, including but not limited to multi-modal driving digital human video generation, digital human real-time interaction, etc. 2. Participate in and promote the implementation of the above related technologies in scenarios such as AIGC creation, marketing Agent, and AI interaction, and support various ByteDance products 3. Produce high-quality, industry-influential work, including technical reports and academic papers.
Qualifications
1. More than two years of working experience in computer vision, AIGC, and multi-modal generation, proficient in various image and video generation algorithms, and experience in the digital human field will be preferred 2. Candidates with in-depth research or project implementation experience in lip-sync/movement generation, Virtual Try-On, multi-modal drive, reinforcement learning, autoregressive generation, face/body 3D reconstruction, expression/motion capture, etc. will be preferred 3. The ability to quickly learn new technologies, enthusiasm for new technologies, and long-term experience in systematic technology construction 4. Applicants who have published papers in top international conferences or journals (including but not limited to CVPR/ICCV/ECCV/NeurIPS/ICML/AAAI/TPAMI/IJCV/SIGRAPH, etc.) will be given priority.