Search Results for author: Majd Hawasly

Found 12 papers, 3 papers with code

Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic

no code implementations23 Oct 2023 Sabri Boughorbel, Majd Hawasly

While significant progress has been made in benchmarking Large Language Models (LLMs) across various tasks, there is a lack of comprehensive evaluation of their abilities in responding to multi-turn instructions in less-commonly tested languages like Arabic.

Benchmarking Instruction Following

Scaling up Discovery of Latent Concepts in Deep NLP Models

1 code implementation20 Aug 2023 Majd Hawasly, Fahim Dalvi, Nadir Durrani

Despite the revolution caused by deep NLP models, they remain black boxes, necessitating research to understand their decision-making processes.

Clustering Decision Making

LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking

1 code implementation9 Aug 2023 Fahim Dalvi, Maram Hasanain, Sabri Boughorbel, Basel Mousi, Samir Abdaljalil, Nizi Nazar, Ahmed Abdelali, Shammur Absar Chowdhury, Hamdy Mubarak, Ahmed Ali, Majd Hawasly, Nadir Durrani, Firoj Alam

Initially developed to evaluate Arabic NLP tasks using OpenAI's GPT and BLOOM models; it can be seamlessly customized for any NLP task and model, regardless of language.

Benchmarking Few-Shot Learning

Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?

no code implementations22 Jun 2022 Aravinda Ramakrishnan Srinivasan, Yi-Shin Lin, Morris Antonello, Anthony Knittel, Mohamed Hasan, Majd Hawasly, John Redford, Subramanian Ramamoorthy, Matteo Leonetti, Jac Billington, Richard Romano, Gustav Markkula

Even though the models' RMSE value differed, all the models captured the kinematic-dependent merging behavior but struggled at varying degrees to capture the more nuanced courtesy lane change and highway lane change behavior.

Autonomous Vehicles

PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving

no code implementations1 Nov 2020 Henry Pulver, Francisco Eiras, Ludovico Carozza, Majd Hawasly, Stefano V. Albrecht, Subramanian Ramamoorthy

In this paper, we present PILOT -- a planning framework that comprises an imitation neural network followed by an efficient optimiser that actively rectifies the network's plan, guaranteeing fulfilment of safety and comfort requirements.

Autonomous Driving Imitation Learning

PaRoT: A Practical Framework for Robust Deep Neural Network Training

1 code implementation7 Jan 2020 Edward Ayers, Francisco Eiras, Majd Hawasly, Iain Whiteside

Deep Neural Networks (DNNs) are finding important applications in safety-critical systems such as Autonomous Vehicles (AVs), where perceiving the environment correctly and robustly is necessary for safe operation.

Adversarial Defense Autonomous Vehicles

CLAD: A Complex and Long Activities Dataset with Rich Crowdsourced Annotations

no code implementations11 Sep 2017 Jawad Tayyub, Majd Hawasly, David C. Hogg, Anthony G. Cohn

This paper introduces a novel activity dataset which exhibits real-life and diverse scenarios of complex, temporally-extended human activities and actions.

Activity Recognition object-detection +1

Natural Language Grounding and Grammar Induction for Robotic Manipulation Commands

no code implementations WS 2017 Muhannad Alomari, Paul Duckworth, Majd Hawasly, David C. Hogg, Anthony G. Cohn

This is achieved by first learning a set of visual {`}concepts{'} that abstract the visual feature spaces into concepts that have human-level meaning.

Estimating Activity at Multiple Scales using Spatial Abstractions

no code implementations25 Jul 2016 Majd Hawasly, Florian T. Pokorny, Subramanian Ramamoorthy

Autonomous robots operating in dynamic environments must maintain beliefs over a hypothesis space that is rich enough to represent the activities of interest at different scales.

Clustering Trajectory Clustering

Bayesian Policy Reuse

no code implementations1 May 2015 Benjamin Rosman, Majd Hawasly, Subramanian Ramamoorthy

We formalise the problem of policy reuse, and present an algorithm for efficiently responding to a novel task instance by reusing a policy from the library of existing policies, where the choice is based on observed 'signals' which correlate to policy performance.

Bayesian Optimisation

Clustering Markov Decision Processes For Continual Transfer

no code implementations15 Nov 2013 M. M. Hassan Mahmud, Majd Hawasly, Benjamin Rosman, Subramanian Ramamoorthy

The source subset forms an `$\epsilon$-net' over the original set of MDPs, in the sense that for each previous MDP $M_p$, there is a source $M^s$ whose optimal policy has $<\epsilon$ regret in $M_p$.

Clustering Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.