Camera Lens
Camera lenses, in their broadest sense, are systems for focusing light to form images, impacting diverse fields from autonomous driving to artistic expression and even large language model (LLM) development. Current research focuses on improving image quality through computational aberration correction and depth-of-field control, often employing novel architectures like diffusion models and leveraging techniques from Riemannian geometry and network flows for enhanced performance. These advancements are crucial for improving the accuracy and reliability of computer vision systems, enabling new applications in various domains, and furthering our understanding of complex data representations.
Papers
When Only Time Will Tell: Interpreting How Transformers Process Local Ambiguities Through the Lens of Restart-Incrementality
Brielen Madureira, Patrick Kahardipraja, David Schlangen
Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
Shahar Katz, Yonatan Belinkov, Mor Geva, Lior Wolf