Sort by
Refine Your Search
-
, and the mathematical and computational foundations of neural networks. Familiarity with the following areas is meritorious: machine learning, computational complexity, tree automata and tree
-
convolutional neural networks by exploring transformers, implicit neural representations (INRs), and hybrid architectures that integrate physical priors such as periodicity, symmetry, and long-range correlations
-
-Brain inspired Neuromorphic Nanophotonics (InsectNeuroNano). The long-term vision of this project is a novel on-chip hybrid nanostructure platform for energy-efficient, fast artificial neural networks and
-
this, we focus on self-supervised denoising, where models learn to restore images using only the noisy data itself — without requiring clean references. Existing approaches often rely on convolutional neural
-
multimodal systems. The emphasis is on agentic approaches, where an LLM interacts with visual tools, which may themselves be neural networks. Central challenges include enabling LLMs to reason about visual
-
on agentic approaches, where an LLM interacts with visual tools, which may themselves be neural networks. Central challenges include enabling LLMs to reason about visual structures, designing