图像/视频生成算法实习生（J102191）
Core
Research and optimize image/video generation models, specifically exploring high-quality and efficient generation schemes under diffusion models (Diffusion/DiT) and generative large models.
Role type
Research intern (image/video generation)
Builds
Production-ready generative models and research prototypes
Domain
Computer Vision / Generative AI
Deliverable
production ML models
Required skills
Deep learning, Diffusion models, Model post-training, Model distillation, Reinforcement learning, Academic writing
Preferred skills
Top-tier conference publications (CVPR/ICCV/NeurIPS/ICLR), Few-shot generation, Inference acceleration
Technologies
Diffusion models, DiT, Reinforcement learning
Responsibilities
Track frontier research in image/video generation and generative large models, explore novel optimization methods, design and validate technical solutions for key challenges
Seniority
Intern
