Paper 'Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation' accepted to NeurIPS 2025.
Paper 'VALLR: Visual ASR Language Model for Lip Reading' accepted to ICCV 2025, achieving state-of-the-art lip reading performance with 99% less training data.
Paper 'Prompt Learning with Optimal Transport for Few-Shot Temporal Action Localization' accepted to ICCV 2025 CLVL Workshop.
Co-chairing the Sign Language Recognition, Translation, and Production (SLRTP) workshop at CVPR 2025.
Chairing the BMVA one-day symposium on AI for Sign Language Translation, Production, and Linguistics in December 2025.