15 papers
Explicit Dropout: Deterministic Regularization for Transformer Architectures
Vidhi Agrawal, Illia Oleksiienko, Alexandros Iosifidis
Dropout is a widely used regularization technique in deep learning, but its effects are typically realized through stochastic masking rather than explicit optimization objectives.…
DeepCoT: Deep Continual Transformers for Real-Time Inference on Data Streams
Ginés Carreto Picón, Peng Yuan Zhou, Qi Zhang +1
Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks. At the same time, there is a growing demand for high perfo…
Delay Bound Relaxation with Deep Learning-based Haptic Estimation for Tactile Internet
Georgios Kokkinis, Alexandros Iosifidis, Qi Zhang
Haptic teleoperation typically demands sub-millisecond latency and ultra-high reliability (99.999%) in Tactile Internet. At a 1 kHz haptic signal sampling rate, this translates int…
Learning hidden cascades via classification
Derrick Gilchrist Edward Manoharan, Anubha Goel, Alexandros Iosifidis +2
The spreading dynamics in social networks are often studied under the assumption that individuals' statuses, whether informed or infected, are fully observable. However, in many re…
LOBERT: Generative AI Foundation Model for Limit Order Book Messages
Eljas Linna, Kestutis Baltakys, Alexandros Iosifidis +1
Modeling the dynamics of financial Limit Order Books (LOB) at the message level is challenging due to irregular event timing, rapid regime shifts, and the reactions of high-frequen…
xHAP: Cross-Modal Attention for Haptic Feedback Estimation in the Tactile Internet
Georgios Kokkinis, Alexandros Iosifidis, Qi Zhang
The Tactile Internet requires ultra-low latency and high-fidelity haptic feedback to enable immersive teleoperation. A key challenge is to ensure ultra-reliable and low-latency tra…