activity
20192021
most citedMapping Low-Resolution Images To Multiple High-Resolution Images Using Non-Adversarial Mapping

2 citations · 3 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CL2021

MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation

Ahmad Rashid, Vasileios Lioutas, Mehdi Rezagholizadeh

The advent of large pre-trained language models has given rise to rapid progress in the field of Natural Language Processing (NLP). While the performance of these models on standar…

stat.ML2021

Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation

Adam Scibior, Vasileios Lioutas, Daniele Reda +2

We develop a deep generative model built on a fully differentiable simulator for multi-agent trajectory prediction. Agents are modeled with conditional recurrent variational neural…

cs.CL2020

Towards Zero-Shot Knowledge Distillation for Natural Language Processing

Ahmad Rashid, Vasileios Lioutas, Abbas Ghaddar +1

Knowledge Distillation (KD) is a common knowledge transfer algorithm used for model compression across a variety of deep learning based natural language processing (NLP) solutions.…

eess.IV20202 cited

Mapping Low-Resolution Images To Multiple High-Resolution Images Using Non-Adversarial Mapping

Vasileios Lioutas

Several methods have recently been proposed for the Single Image Super-Resolution (SISR) problem. The current methods assume that a single low-resolution image can only yield a sin…

cs.LG2020

Time-aware Large Kernel Convolutions

Vasileios Lioutas, Yuhong Guo

To date, most state-of-the-art sequence modeling architectures use attention to build generative models for language based tasks. Some of these models use all the available sequenc…

cs.CL2019

Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition

Vasileios Lioutas, Ahmad Rashid, Krtin Kumar +2

Word-embeddings are vital components of Natural Language Processing (NLP) models and have been extensively explored. However, they consume a lot of memory which poses a challenge f…