Summary:
This candidate is expected to:
· Conduct original research in computer vision and related areas (e.g., 3D reconstruction, vision language model, multimodal generative modeling), from conceptualization through implementation and evaluation.
· Identify state-of-the-art (SOTA) techniques, performing systematic literature reviews and benchmarking existing methods to inspire new ideas.
· Conduct experimental studies and refine solutions based on qualitative evaluation and quantitative metrics.
· Write research papers and publish findings in top-tier CV/ML conferences and journals.
· Deep understanding of computer vision and machine learning fundamentals
· Strong programming skills in Python and hands-on experience with frameworks such as PyTorch, etc.
· Proven experience in conducting original research in computer vision, with at least one publication in a peer-reviewed journal or conference
· Strong written and verbal communication skills, with the ability to contribute to academic publications and present research findings
· Ability to work independently and collaborate effectively within a team
· PhD student in Computer Science, Computer Vision, Machine Learning, or a related field