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