Abdulqader Dhafer | عبد القادر ظافر

aamd2 [at] leicester [dot] ac [dot] uk

I am a first-year Computer Science PhD student at the University of Leicester, working within DANiLab and under the supervision of Dr. Daniel Zhou Hao and Dr. Tim Pearce. I received my MComp (undergraduate with integrated master's) in Computer Science from the University of Leicester University of Leicester in 2025, where I graduated with first-class honours.

LinkedIn

profile photo

Research

I am interested in World Action Models (WAMs), Vision-Language-Action Models (VLAs), and robotic locomotion and navigation, towards building more capable, generalisable embodied agents.

Embodied Interpretability teaser Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models
Hanxin Zhang, Mingshuo Xu, Abdulqader Dhafer, Shigang Yue, Hongbiao Dong, Zhou Daniel Hao
ICML 2026  /  project page / bibtex

A causal interpretability framework for Vision-Language-Action models that diagnoses generalisation by measuring reliance on task-relevant versus spurious visual features.