Master Thesis in Emergent Width-Adaptive Representations via Spatially-Gated Channel Routing
Core
Developing a novel transformer architecture for autonomous driving perception that adaptively adjusts computational depth and width.
Role type
Master thesis researcher (deep learning & computer vision)
Builds
Efficient transformer models for semantic segmentation and object detection
Domain
Autonomous driving, deep learning, computer vision
Deliverable
production ML models
Required skills
deep learning concepts, PyTorch, Python programming
Responsibilities
develop and implement adaptive transformer architecture, design and conduct experiments to assess model performance and efficiency, analyze emergent network properties regarding resource allocation and feature organization
Sourced via smartrecruiters · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
