| 查看: 598 | 回复: 0 | |||
[交流]
Position: Ph.D. Student in Generative AI - Controllable Video Generation at UNSW
|
|
Supervisors: Dr. Huadong Mo (UNSW) & Professor Daoyi Dong (ANU) (mainly work with Mr Zhenhong Sun - https://scholar.google.com.hk/ci ... AJ&hl=zh-CN and Dr Junyan Wang - https://scholar.google.com/citat ... AAAJ&hl=en) Position Overview: Our lab is recruiting Ph.D. students to focus on advanced research in Generative AI, particularly in controllable video generation. This research will involve the development of state-of-the-art algorithms in Diffusion Models, Large Language Models (LLMs), and 3D generation technologies. The aim is to enhance the quality and controllability of generated video content and explore the integration of multimodal interactions in video generation. Under the supervision of Dr. Huadong Mo and Professor Daoyi Dong, this position provides an excellent environment and platform for innovative research. Research Focus and Responsibilities: * Develop and research Diffusion Model-based methods for time-series video generation, focusing on high-quality and highly controllable video output * Leverage Large Language Models (LLMs) to guide video generation, ensuring semantic consistency and contextual alignment * Explore 3D generation and rendering techniques, integrating multimodal data such as text, images, and video * Enhance model controllability to enable specific, condition-based video generation * Write and publish high-quality research papers and present findings at international conferences and journals Position Requirements: * Educational Background: A Master’s degree (or exceptional Bachelor’s degree) in Computer Science, Artificial Intelligence, Machine Learning, or a related field * Technical Skills: * Strong understanding of Diffusion Models and their applications in image and video generation * Familiarity with the fundamentals of Large Language Models (LLMs) and their use in generative tasks * Basic knowledge of 3D generation and rendering techniques and an understanding of multimodal data integration * Programming Skills: Proficiency in Python and experience with deep learning frameworks (e.g., PyTorch or TensorFlow) * Research Skills: Strong literature review and analysis abilities, with a capacity to design experiments and analyze data independently * Collaboration Skills: Excellent communication and teamwork abilities Preferred Qualifications: * Publications in top-tier conferences or journals related to Generative AI * Project experience in generative models, video generation, or 3D modeling * Familiarity with 3D rendering engines such as Blender or Unity * Hands-on experience with cross-modal generation (e.g., text-to-video, image-to-video) We Offer: * An intellectually stimulating environment with abundant research resources * Guidance from Dr. Huadong Mo and Professor Daoyi Dong, with a focus on student growth in both academic and career development * Opportunities to work on cutting-edge research in Generative AI, fostering advanced research skills and innovative thinking Please get in touch with Dr Mo at huadong.mo@unsw.edu.au for more information. |
回复此楼» 猜你喜欢
【博士招生】太原理工大学2026化工博士
已经有4人回复
-
什么是人一生最重要的？
已经有5人回复
-
280求调剂
已经有3人回复
-
网上报道青年教师午睡中猝死、熬夜猝死的越来越多，主要哪些原因引起的？
已经有8人回复
-
面上可以超过30页吧？
已经有11人回复
-
版面费该交吗
已经有15人回复
-
体制内长辈说体制内绝大部分一辈子在底层，如同你们一样大部分普通教师忙且收入低
已经有18人回复
-
为什么中国大学工科教授们水了那么多所谓的顶会顶刊，但还是做不出宇树机器人？
已经有10人回复