Postdoctoral Fellow / Senior Research Fellow in Vision Language Models

Tasks

• Collaborate with industry partners
• Conduct research on vision language models
• Develop and evaluate multimodal benchmarks
• Develop continual learning approaches
• Handle multimodal data processing
• Perform model pretraining and posttraining
• Present findings at conferences and workshops
• Supervise HDR students
• Write scientific papers and reports

Perks/Benefits

• N/A

Skills/Tech-stack

Benchmark development | Computer Vision | Continual Learning | Deep learning | Language Models | Model Editing | Model pretraining | Multimodal Data | Post Tuning | Software Engineering | Vision Language Models | Vision-language