Marco Pedersoli

11

Papers

10

Total Citations

Papers (11)

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

NeurIPS 2025arXiv

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

StarVector: Generating Scalable Vector Graphics Code from Images and Text

Visual Modality Prompt for Adapting Vision-Language Object Detectors

Modality Translation for Object Detection Adaptation without forgetting prior knowledge

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

NeurIPS 2025arXiv

LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups

NeurIPS 2025arXiv

Re-Basin via Implicit Sinkhorn Differentiation

Augmented Lagrangian Adversarial Attacks

A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses

Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels

NeurIPS 2021arXiv