Paolo Garza

3 papers · 2023–2024 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ACL (1) EMNLP (1) SemEval (1)

Top co-authors

Luca Cagliero (3) Lorenzo Vaiani (2) Daniele Rege Cambrin (1) Caren Han (1) Irene Benedetto (1) Jean Lee (1) Yihao Ding (1) Josiah Poon (1) Giuseppe Gallipoli (1)

Research topics

Artificial Intelligence (2) Machine Learning (2) Core AI (2) Deep Learning (1) Natural Language Processing (1) Application Areas (1) Learning Paradigms (1) Learning Types (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1) Understanding (1)

Keywords

multimodal learning (2) multi-task learning (1) knowledge distillation (1) text generation (1) loss function (1) image-text retrieval (1) cross-entropy loss (1) clip model (1) focal loss (1) language model fine-tuning (1) large language model (1) visually-rich document (1) lovasz loss (1) visual word sense disambiguation (1) semantic segmentation (1) form document understanding (1)

Papers

3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding ACL 2024 Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning EMNLP 2024 PoliTo at SemEval-2023 Task 1: CLIP-based Visual-Word Sense Disambiguation Based on Back-Translation SemEval 2023