activity
20242026
collaborators

5 papers

cs.LG2026

Recursive Scaling in Masked Diffusion Models

Alba Carballo-Castro, Julianna Piskorz, Paulius Rauba +2

Masked diffusion models (MDMs) have recently emerged as a promising paradigm for sequence generation. Scaling MDMs is conventionally achieved by increasing the parameter count or t…

cs.LG2026

Fixed-Point Masked Generative Modeling

Andrea Miele, Yiming Qin, Alba Carballo-Castro +2

Masked Generative Models (MGMs) enable parallel decoding and achieve strong performance across modalities, but require full-sequence bidirectional transformers at every step, makin…

cs.LG2026

Balancing Symmetry and Efficiency in Graph Flow Matching

Benjamin Honoré, Alba Carballo-Castro, Yiming Qin +1

Equivariance is central to graph generative models, as it ensures the model respects the permutation symmetry of graphs. However, strict equivariance can increase computational cos…

cs.LG2025

Generating Directed Graphs with Dual Attention and Asymmetric Encoding

Alba Carballo-Castro, Manuel Madeira, Yiming Qin +2

Directed graphs naturally model systems with asymmetric, ordered relationships, essential to applications in biology, transportation, social networks, and visual understanding. Gen…

cs.LG2024

Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks

Alba Carballo-Castro, Sonia Laguna, Moritz Vandenhirtz +1

Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable. However, concept annotations are gen…