Pawin Taechoyotin

Pawin Taechoyotin

PhD Student in the Department of Computer Science

Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

Health link: scalable health information exchange platform in Thailand

Published in 2021 2nd International Conference on Big Data Analytics and Practices (IBDAP), 2021

This paper proposes a hybrid scalable health information exchange platform in Thailand. Such system expedites the process of referrel, general treatment, and safety in emergency cases. The results show that interoperability, privacy, and security can be implemented with Fast Healthcare Interoperability Resources (FHIR), pseudonymization, and access control respectively.

Recommended citation: Taechoyotin, P., Prasertsom, P., Phanhong, M., Wongsutthikoson, P., Laohasurayodhin, R., Pasuthip, N., & Ruktantichoke, B. (2021, August). Health link: scalable health information exchange platform in Thailand. In 2021 2nd International Conference on Big Data Analytics and Practices (IBDAP) (pp. 101-106). IEEE.
Download Paper

Workshop Papers

MAMORX: Multi-agent multi-modal scientific review generation with external knowledge

Published in Neurips 2024 Workshop Foundation Models for Science: Progress, Opportunities, and Challenges, 2024

This paper proposes a multi-agent framework that generates peer review comments based on text, figures, common knowledge, and a database of known literature.

Recommended citation: Taechoyotin, P., Wang, G., Zeng, T., Sides, B., & Acuna, D. (2024, October). MAMORX: Multi-agent multi-modal scientific review generation with external knowledge. In Neurips 2024 Workshop Foundation Models for Science: Progress, Opportunities, and Challenges.
Download Paper

MISTI: Metadata-Informed Scientific Text and Image Representation through Contrastive Learning

Published in Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024), 2024

This paper utilized contrastive learning to create better image-text embeddings/representation of scientific figure and captions leading higher performance in information retrieval task. The captions were augmented with metadata found only in scientific manuscripts which resulted in improved grouping between figure/caption within the same field, section, and topic.

Recommended citation: Taechoyotin, P., & Acuna, D. (2024, August). MISTI: Metadata-Informed Scientific Text and Image Representation through Contrastive Learning. In Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024) (pp. 155-164).
Download Paper

Preprints

REMOR: Automated Peer Review Generation with LLM Reasoning and Multi-Objective Reinforcement Learning

Published in arXiv preprint arXiv:2505.11718, 2025

This paper proposes a multi-objective reward function to quantify the quality of peer review comments and train a LLM via Reinforcement Learning based-on the reward function for better peer review comments.

Recommended citation: Taechoyotin, P., & Acuna, D. (2025). REMOR: Automated Peer Review Generation with LLM Reasoning and Multi-Objective Reinforcement Learning. arXiv preprint arXiv:2505.11718.
Download Paper