About Me
Vasco Ramos is a PhD Researcher in Multimodal AI at NOVA University of Lisbon in partnership with Google, where he investigates on how to measure and improve factuality on image and video generative methods. Recognized for his academic excellence as a top graduate during BSc and MSc, his team achieved 1st Place in the Amazon Alexa Prize TaskBot Challenge 2 for developing a multimodal conversational agent.
Publications
2025
 | Beyond the Noise: Aligning Prompts with Latent Representations in Diffusion Models Vasco Ramos, Regev Cohen, Idan Szpektor, Joao Magalhaes arXiv preprint arXiv:2512.08505, 2025 [Paper] [Code] |
 | Contrastive Sequential-Diffusion Learning: Non-Linear and Multi-Scene Instructional Video Synthesis Vasco Ramos, Yonatan Bitton, Michal Yarom, Idan Szpektor, Joao Magalhaes IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025 [Paper] [Code] [Video] |
 | Latent Beam Diffusion Models for Generating Visual Sequences Guilherme Fernandes, Vasco Ramos, Regev Cohen, Idan Szpektor, Joao Magalhães arXiv preprint arXiv:2503.20429, 2025 [Paper] [Code] |
2024
 | Generating coherent sequences of visual illustrations for real-world manual tasks João Bordalo, Vasco Ramos, Rodrigo Valério, Diogo Glória-Silva, Yonatan Bitton, Michal Yarom, Idan Szpektor, Joao Magalhaes Association for Computational Linguistics (ACL), 2024 [Paper] [Code] |
2023
 | TWIZ: The wizard of multimodal conversational-stimulus Rafael Ferreira, Diogo Tavares, Diogo Silva, Rodrigo Valério, João Bordalo, Inês Simões, Vasco Ramos, David Semedo, Joao Magalhaes Alexa Prize TaskBot Challenge 2 Proceedings, 2023 [Paper] [Code] |
Teaching
- Natural Language Processing, 2025, CMU Portugal Advanced Training Program
- Multimodal Generative AI, 2025, CMU Portugal Advanced Training Program
- Deep Learning, 2024, Samsung Innovation Campus Artificial Intelligence Course