Generative AI Research Intern - Image-to-Video Diffusion
Apple
1 day ago
Internship
On-site
Beijing, Beijing, United States
We are seeking a talented Generative AI Research Intern to work on image-to-video (I2V) diffusion models. This role focuses on building next-generation generative systems that transform still images into high-quality, temporally consistent videos. You will work closely with researchers and engineers to explore cutting-edge diffusion and transformer-based architectures for video generation, motion modeling, and temporal representation learning.\\n
You will: \\n- Lead experimental studies on image-to-video diffusion techniques and temporal generative modeling.\\n- Design, implement, and evaluate model variants for motion modeling and temporal consistency.\\n- Build experimental pipelines and run ablation studies and benchmarking experiments.\\n- Analyze results and summarize findings in internal research reports or presentations.\\n- Study and reproduce recent work in video diffusion and I2V generation.\\n- Participate in research discussions and proposal of new ideas.
Currently pursuing a Master’s or Ph.D. degree in Computer Science, Electrical Engineering, Applied Mathematics, or a related field.\\nStrong background in computer vision and deep learning, with research or project experience in diffusion models, flow-matching, or transformer-based generative models applied to video generation or spatiotemporal tasks.\\nExperience or solid understanding of image-to-video models, video generation, temporal modeling, or video representation.\\nProficiency in Python and PyTorch, with the ability to implement research code independently.\\nFamiliarity with model training workflows, ablation studies, and experimental result analysis.\\nFamiliarity with generative video evaluation metrics such as LPIPS, FVD, and perceptual assessment methods.\\nStrong motivation for independent research and the ability to drive projects with minimal supervision.\\nAbility to read, reproduce, and critically analyze recent research papers.
Understanding of video fundamentals such as motion estimation, optical flow, temporal consistency, or alignment techniques.\\nPrior experience with large-scale training, multimodal models, or video datasets.\\nPublications in top-tier conferences or journals (e.g., CVPR, ICCV, ECCV, NeurIPS, ICLR, etc.).\\nStrong curiosity and motivation for independent research in generative video modeling.
You will: \\n- Lead experimental studies on image-to-video diffusion techniques and temporal generative modeling.\\n- Design, implement, and evaluate model variants for motion modeling and temporal consistency.\\n- Build experimental pipelines and run ablation studies and benchmarking experiments.\\n- Analyze results and summarize findings in internal research reports or presentations.\\n- Study and reproduce recent work in video diffusion and I2V generation.\\n- Participate in research discussions and proposal of new ideas.
Currently pursuing a Master’s or Ph.D. degree in Computer Science, Electrical Engineering, Applied Mathematics, or a related field.\\nStrong background in computer vision and deep learning, with research or project experience in diffusion models, flow-matching, or transformer-based generative models applied to video generation or spatiotemporal tasks.\\nExperience or solid understanding of image-to-video models, video generation, temporal modeling, or video representation.\\nProficiency in Python and PyTorch, with the ability to implement research code independently.\\nFamiliarity with model training workflows, ablation studies, and experimental result analysis.\\nFamiliarity with generative video evaluation metrics such as LPIPS, FVD, and perceptual assessment methods.\\nStrong motivation for independent research and the ability to drive projects with minimal supervision.\\nAbility to read, reproduce, and critically analyze recent research papers.
Understanding of video fundamentals such as motion estimation, optical flow, temporal consistency, or alignment techniques.\\nPrior experience with large-scale training, multimodal models, or video datasets.\\nPublications in top-tier conferences or journals (e.g., CVPR, ICCV, ECCV, NeurIPS, ICLR, etc.).\\nStrong curiosity and motivation for independent research in generative video modeling.