Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks Safety4ConvAI WS

Georgios Pantazopoulos | Amit Parekh | Malvina Nikandrou | Alessandro Suglia |

Lost in Space: Probing Fine-grained Spatial Understanding in Vision and Language Resamplers NAACL

Georgios Pantazopoulos | Alessandro Suglia | Oliver Lemon | Arash Eshghi |

Enhancing Continual Learning in Visual Question Answering with Modality-Aware Feature Distillation ALVR WS

Malvina Nikandrou | Georgios Pantazopoulos | Ioannis Konstas | Alessandro Suglia |

Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling EMNLP

Georgios Pantazopoulos | Malvina Nikandrou | Alessandro Suglia | Oliver Lemon | Arash Eshghi |

Multitask Multimodal Prompted Training for Interactive Embodied Task Completion EMNLP

Georgios Pantazopoulos | Malvina Nikandrou | Amit Parekh | Bhathiya Hemanthage | Arash Eshghi | Ioannis Konstas | Verena Rieser | Oliver Lemon | Alessandro Suglia |