About
Research & Development
FLAIR: A Novel Framework for High-Fidelity Implicit Neural Representations
TLDR: FLAIR is a new framework for Implicit Neural Representations (INRs) that addresses issues like spectral bias and poor high-frequency detail capture. It introduces...
Research & Development
Seeing and Hearing: A New Approach to Cochlear Implant Sound Processing in Noisy Environments
TLDR: A new end-to-end cochlear implant (CI) system, AVSE-ECS, integrates audio-visual speech enhancement with a deep-learning-based sound coding strategy. By using visual cues like...
Research & Development
Navigating Causal Uncertainty: A Comprehensive Study of Bounding Algorithms
TLDR: This research paper by Tobias Anton Maringgele explores 'partial identification' in causal inference, a method that provides a range (bounds) for causal effects...
Research & Development
Enhancing Spiking Neural Networks with Multiple Interacting Learning Mechanisms
TLDR: A new framework called Multi-Plasticity Synergy Learning (MPSL) improves Spiking Neural Network (SNN) training by integrating multiple learning mechanisms like STBP, Hebbian, and...
Research & Development
Enhancing Multi-Image Understanding in Vision-Language Models with FOCUS
TLDR: FOCUS is a new training-free decoding strategy that improves Large Vision-Language Models' (LVLMs) ability to handle multiple images by preventing "cross-image information leakage."...
Research & Development
PENGUIN: A New Approach to Long-term Time Series Forecasting with Enhanced Attention
TLDR: PENGUIN is a novel Transformer-based model that significantly improves long-term time series forecasting by explicitly modeling periodic patterns and incorporating a periodic-nested group...