Computer Vision

MERL is looking for research interns to conduct research into novel architectures for "small" large generative models. We are currently exploring 0.5 - 2 billion parameter language models, text-to-image models and text-to-video models. Interesting research directions include (a) efficient learning for such models that improves the pareto front of current scaling laws for these sizes, (b) enhancing current transformer-based architectures, and (c) new architectural paradigms beyond transformers such as incorporating explicitly temporal designs. Prior experience with machine learning/computer vision/natural language processing research, and proficiency in building and experimenting with machine learning models using a framework like PyTorch are required. Candidates well into their PhD program with publications in top-tier machine learning, natural language processing or computer vision venues, ideally connected to building generative models, are strongly preferred. Candidates are also expected to collaborate with MERL researchers for preparing manuscripts for scientific publications based on the results obtained during the internship. Duration of the internship is 3 months with a flexible start date.

Required Specific Experience

• Research experience with recent vision and text generative models
• Deep understanding of neural network architectures
• Proficiency in machine learning frameworks like PyTorch

MERL is seeking a motivated intern to assist in developing hardware and algorithms for multimodal imaging applications. The project involves integration of radar, camera, and depth sensors in a variety of sensing scenarios. The ideal candidate should have experience with FMCW radar and/or depth sensing, and be fluent in Python and scripting methods. Familiarity with optical tracking of humans and experience with hardware prototyping is desired. Good knowledge of computational imaging and/or radar imaging methods is a plus.

Required Specific Experience

• Experience with Python and Python Deep Learning Frameworks.
• Experience with FMCW radar and/or Depth Sensors.

MERL is looking for a highly motivated and qualified PhD student in the areas of machine learning and robotics, to participate in research on advanced algorithms for learning control of robots and other mechanisms. Solid background and hands-on experience with various machine learning algorithms is expected, and in particular with deep learning algorithms for image processing and object detection. Exposure to deep reinforcement learning and/or learning from demonstration is highly desirable. Familiarity with the use of machine learning algorithms for system identification of mechanical systems would be a plus, along with background in other areas of automatic control. Solid experimental skills and hands-on experience in coding in Python, PyTorch, and OpenCV are required for the position. Some experience with ROS2 and familiarity with classical mechanics and computational physics engines would be helpful, but is not required. The position will provide opportunities for exploring fundamental problems in incremental learning in humans and machines, leading to publishable results. The duration of the internship is 3 to 5 months, with a flexible starting date.

Required Specific Experience

• Python, PyTorch, OpenCV