AIConfPaper
← Search

Majd Hawasly

7 accepted papers

2026

SpatiaLab: Can Vision–Language Models Perform Spatial Reasoning in the Wild?

Azmine Toushik Wasi, Wahid Faisal, Abdur Rahman, Mahfuz Ahmed Anik, Munem Shahriar, Mohsin Mahmud Topu +9
ICLR 2026poster

Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision–language models (VLMs). Prior work largely relied on synthetic or LLM-generated environments with limited task designs and puzzle-like setups, failing to capture the real-world comp…

Cited by 0Source ↗code ↗Scholar ↗
2025

Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing

Sabri Boughorbel, Fahim Dalvi, Nadir Durrani, Majd Hawasly
EMNLP 2025

As fine-tuning becomes the dominant paradigm for improving large language models (LLMs), understanding what changes during this process is increasingly important. Traditional benchmarking often fails to explain _why_ one model outperforms another. In this work, we use model diffing, a mechanistic in

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Exploring Alignment in Shared Cross-lingual Spaces

Basel Mousi, Nadir Durrani, Fahim Dalvi, Majd Hawasly, Ahmed Abdelali
ACL 2024long

Despite their remarkable ability to capture linguistic nuances across diverse languages, questions persist regarding the degree of alignment between languages in multilingual embeddings. Drawing inspiration from research on high-dimensional representations in neural language models, we employ cluste…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

DiPA: Probabilistic Multi-Modal Interactive Prediction for Autonomous Driving

Anthony Knittel, Majd Hawasly, Stefano V. Albrecht, John Redford, Subramanian Ramamoorthy
RA-L 2023

Accurate prediction is important for operating an autonomous vehicle in interactive scenarios. Prediction must be fast, to support multiple requests from a planner exploring a range of possible futures. The generated predictions must accurately represent the probabilities of predicted trajectories,

Cited by 12Source ↗Scholar ↗
2021

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

Henry Pulver, Francisco Eiras, Ludovico Carozza, Majd Hawasly, Stefano V. Albrecht, Subramanian Ramamoorthy
IROS 2021poster

Achieving a proper balance between planning quality, safety and efficiency is a major challenge for autonomous driving. Optimisation-based motion planners are capable of producing safe, smooth and comfortable plans, but often at the cost of runtime efficiency. On the other hand, naïvely deploying tr…

Cited by 31Source ↗Scholar ↗
2020

FPR - Fast Path Risk Algorithm to Evaluate Collision Probability

Andrew Blake, Alejandro Bordallo, Kamen Brestnichki, Majd Hawasly, Svetlin Valentinov Penkov, Subramanian Ramamoorthy +1
RA-L 2020

As mobile robots and autonomous vehicles become increasingly prevalent in human-centred environments, there is a need to control the risk of collision. Perceptual modules, for example machine vision, provide uncertain estimates of object location. In that context, the frequently made assumption of a

Cited by 7Source ↗Scholar ↗