arxiv:2407.11814
Vasco Ramos
asiimo
ยท
AI & ML interests
Multimodal Generation, Factual Consistency
Recent Activity
upvoted
an
article
about 21 hours ago
Explaining the SDXL latent space
authored
a paper
4 months ago
Contrastive Sequential-Diffusion Learning: An approach to Multi-Scene
Instructional Video Synthesis
authored
a paper
about 1 year ago
Generating Coherent Sequences of Visual Illustrations for Real-World
Manual Tasks
Organizations
