Marco Pedersoli

Associate Professor@École de technologie supérieure, Université du Québec·加拿大·OpenReview

研究方向

Learning with reduced resources · Convolutional Neural Networks · Weakly supervised learning · Efficient Deep Learning · Recurrent Neural Networks · Image Captioning

Marco Pedersoli

BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change

Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method

VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors

VectorGym: A Multi-Task Benchmark for SVG Code Generation and Manipulation

AInstein: Assessing the Feasibility of AI-Generated Approaches to Research Problems

Revisiting Mixout: An Overlooked Path to Robust Finetuning

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

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

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

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

Neural Architecture Search by Learning a Hierarchical Search Space

RSMerge: Bridging Head and Tail Classes via Subsampled Model Merging

WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average