Scholar
Andrei C. Coman
Google Scholar ID: LZLaA4cAAAAJ
HES-SO
Citations & Impact
Citations
57
H-index
4
i10-index
2
Publications
13
Co-authors
0
Resume (English only)
Academic Achievements
- - 2025 Paper: RAGferee: Building Contextual Reward Models for Retrieval-Augmented Generation (EMNLP 2025)
- - 2025 Paper: Fast-and-Frugal Text-Graph Transformers are Effective Link Predictors (ACL 2025 Findings)
- - 2025 Paper: Fine-tuning pretrained models with NVIB for improved generalisation (ICLR 2025 SCSL Workshop)
- - 2024 Paper: GADePo: Graph-Assisted Declarative Pooling Transformers for Document-Level Relation Extraction (ACL 2024 KnowledgeNLP Workshop)
- - 2024 Paper: Enhancing Biomedical Knowledge Discovery for Diseases: An End-To-End Open-Source Framework (IEEE Access)
- - 2023 Paper: Strong and Efficient Baselines for Open Domain Conversational Question Answering (EMNLP 2023 Findings)
- - 2023 Paper: Transformers as Graph-to-Graph Models (EMNLP 2023 Big Picture Workshop)
- - 2021 Paper: Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning (CoNLL 2021)
- - 2019 Paper: An incremental turn-taking model for task-oriented dialog systems (INTERSPEECH 2019)
- - 2018 Paper: Exploiting deep neural networks for tweet-based emoji prediction (AI*IA 2018 NL4AI Workshop)
- - 2018 Paper: Predicting emoji exploiting multimodal data: FBK participation in ITAmoji task (CLiC-it 2018 EVALITA Workshop)
Research Experience
- - Postdoctoral Researcher at HES-SO Valais-Wallis AISLab
- - Applied Scientist Intern at Amazon AGI, contributing to retrieval-augmented generation systems and contextual reward modelling projects
Education
- - PhD: Idiap Research Institute & École Polytechnique Fédérale de Lausanne (EPFL), focusing on deep learning architectures for natural language processing, particularly at the intersection of text and graph representation learning
- - Time: Not explicitly provided
Background
- - Research Interests: Deep learning architectures, natural language processing, text and graph representation learning
- - Professional Field: Applied scientific research
- - Brief Introduction: Currently a Postdoctoral Researcher in the AISLab at HES-SO Valais-Wallis. Before joining HES-SO Valais-Wallis, he completed his PhD at the Idiap Research Institute and the École Polytechnique Fédérale de Lausanne (EPFL), focusing on deep learning architectures for natural language processing, particularly at the intersection of text and graph representation learning. He also gained experience as an Applied Scientist Intern at Amazon AGI, where he contributed to retrieval-augmented generation systems and contextual reward modelling.
Miscellany
- - Personal Interests: Values open, respectful, and collaborative work environments, and believes that progress in science and technology is best achieved through kindness, curiosity, and shared effort.
Co-authors