Marco Pedersoli

papers

421

total citations

papers (11)

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

ECCV 2020arXiv

184

citations

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

NEURIPS 2021arXiv

citations

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

ICLR 2025arXiv

citations

Modality Translation for Object Detection Adaptation without forgetting prior knowledge

ECCV 2024arXiv

citations

Visual Modality Prompt for Adapting Vision-Language Object Detectors

ICCV 2025arXiv

citations

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

NEURIPS 2025arXiv

citations

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

NEURIPS 2025arXiv

citations

Marco Pedersoli

papers (11)

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

Re-Basin via Implicit Sinkhorn Differentiation

Augmented Lagrangian Adversarial Attacks

StarVector: Generating Scalable Vector Graphics Code from Images and Text

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

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

Modality Translation for Object Detection Adaptation without forgetting prior knowledge

Visual Modality Prompt for Adapting Vision-Language Object Detectors

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

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

papers (11)

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

Re-Basin via Implicit Sinkhorn Differentiation

Augmented Lagrangian Adversarial Attacks

StarVector: Generating Scalable Vector Graphics Code from Images and Text

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

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

Modality Translation for Object Detection Adaptation without forgetting prior knowledge

Visual Modality Prompt for Adapting Vision-Language Object Detectors

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

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