CV
Education
- 2026Universidad de los AndesGPA: 4.78/5.00
- 2024Universidad de los AndesGPA: 4.58/5.00
Skills
Publications
Conferences
- Online Language Adaptive Sampling for Better Distributed Cross-lingual Gains2026Nguyen, Q. P., Gaschi, F., Anugraha, D., Martínez Novoa, S., & Lee, E.-S. A. (2026). Online Language Adaptive Sampling for Better Distributed Cross-lingual Gains. In Findings of the Association for Computational Linguistics: EMNLP 2026, pp. 36873-36891. Association for Computational Linguistics. https://doi.org/10.18653/2026.findings-emnlp.1724
- SciBETO: A Domain-Specific RoBERTa Model Trained on Spanish Scientific Texts2026Prieto, J. C., Martínez Novoa, S., Gómez Mesa, L., & Manrique, R. (2026). SciBETO: A Domain-Specific RoBERTa Model Trained on Spanish Scientific Texts. Under review for EACL 2027.
- Centralizing the Student Lens: Design and Evaluation of a Learning Analytics Dashboard for Academic Advising in Higher Education2026Martínez Novoa, S., Melo Barrero, F., Ruiz Giraldo, M., Velásquez Marín, S., Carvajal Chaves, N., Hernández Hoyos, M., & Reyes, J. P. (2026). Centralizing the Student Lens: Design and Evaluation of a Learning Analytics Dashboard for Academic Advising in Higher Education. To appear in Proceedings of the World Engineering Education Forum, WEEF (IFEES & GEDC) 2026, Cartagena de Indias, Colombia.
- No Student Left in Limbo: Multi-Level Clustering for Success Prediction in a Latin American University2026Soto Parada, E. G., Martínez Novoa, S., Klopstock Triana, N., Fuquen Florez, D. A., Peña, F. C., Hernández Hoyos, M., & Reyes, J. P. (2026). No Student Left in Limbo: Multi-Level Clustering for Success Prediction in a Latin American University. In Artificial Intelligence in Education (AIED 2026, WideAIED Track), Communications in Computer and Information Science, pp. 63-77. Springer. https://doi.org/10.1007/978-3-032-29791-4_5
Workshops
- MeSHClass-ES and AnatEM-ES: Open Resources for Spanish Biomedical NLP2026Martínez Novoa, S., Gómez Mesa, L., Prieto, J., & Manrique, R. (2026). MeSHClass-ES and AnatEM-ES: Open Resources for Spanish Biomedical NLP. In BioNLP 2026, pp. 617-629. Association for Computational Linguistics. https://doi.org/10.18653/v1/2026.bionlp-1.49
Preprints
- Classification of Chest XRay Diseases through image processing and analysis techniques2026Martínez Novoa, S., Ibáñez, M. C., Gómez Mesa, L., & Kramer, J. (2026). Classification of Chest XRay Diseases through image processing and analysis techniques. arXiv preprint arXiv:2601.10913.
- Efficient Multilingual Dialogue Processing via Translation Pipelines and Distilled Language Models2026Martínez Novoa, S., Rozo Fajardo, N., González Vargas, D. A., & Bedoya Figueroa, N. (2026). Efficient Multilingual Dialogue Processing via Translation Pipelines and Distilled Language Models. arXiv preprint arXiv:2601.09059.
Theses
- Detection and Segmentation of Malignant Melanoma Regions in Dermoscopic Images Using Machine Learning2024Martínez Novoa, S. (2024). Detection and Segmentation of Malignant Melanoma Regions in Dermoscopic Images Using Machine Learning. Undergraduate thesis, Universidad de Los Andes. Supervisor: Juan Pablo Reyes Gómez Ph.D. Uniandes Repository.
Teaching
- {"es"=>"Aplicaciones Basadas en LLM y Construcción de Agentes", "en"=>"LLM-Based Applications & Agent Development"}Universidad de los Andes{"es"=>"Asistente graduado durante tres semestres de dos cursos secuenciales de maestría de 8 semanas cada uno, 'Aplicaciones Basadas en LLM' (sistemas RAG) y 'Construcción de Agentes', con más de 200 estudiantes.", "en"=>"Graduate TA across three semesters for two sequential 8-week master's courses, 'LLM-Based Applications' (RAG systems) and 'Agent Development', supporting over 200 master's students."}{"es"=>"Creé los tutoriales, proyectos y materiales de los módulos de sistemas RAG y de desarrollo de agentes, construidos sobre LangChain, LangGraph, LangSmith y RAGAS.", "en"=>"Created the tutorials, projects, and course materials for the RAG systems and agent development modules, built on LangChain, LangGraph, LangSmith, and RAGAS."}
- {"es"=>"Centro de Apoyo en Programación CupiTaller", "en"=>"CupiTaller Programming Support Center"}{"es"=>"Departamento de Ingeniería de Sistemas y Computación, Universidad de los Andes", "en"=>"Systems and Computing Engineering Department, Universidad de los Andes"}{"es"=>"Como parte del equipo de 7 personas que coordinaba CupiTaller, el centro de apoyo en programación de la universidad, supervisé a más de 110 tutores y asistentes y diseñé los proyectos del curso introductorio, de más de 1100 estudiantes por semestre.", "en"=>"As part of the 7-person team coordinating CupiTaller, the university's programming support center, supervised over 110 tutors and TAs and designed the projects for the introductory course of over 1,100 students per semester."}
- {"es"=>"Centro de Apoyo en Programación", "en"=>"Programming Support Center"}{"es"=>"Departamento de Ingeniería de Sistemas y Computación, Universidad de los Andes", "en"=>"Systems and Computing Engineering Department, Universidad de los Andes"}{"es"=>"Acompañé a más de 100 estudiantes en los fundamentos de programación en Python, con 5 horas semanales de tutoría durante dos años en el centro de apoyo de la universidad.", "en"=>"Tutored over 100 students in Python programming fundamentals, 5 hours a week for two years at the university's programming support center."}
- {"es"=>"Introducción a la Programación", "en"=>"Introduction to Programming"}Universidad de los Andes{"es"=>"Apoyé al profesor en los laboratorios de programación, asistiendo a unos 40 estudiantes por semestre y calificando los proyectos del curso.", "en"=>"Assisted the professor in programming labs of about 40 students per semester, grading the course projects."}
- {"es"=>"Fundamentos de Infraestructura Tecnológica", "en"=>"Fundamentals of Technological Infrastructure"}Universidad de los Andes{"es"=>"Califiqué exámenes y actividades y acompañé a unos 40 estudiantes en los fundamentos de infraestructura tecnológica.", "en"=>"Graded exams and coursework while guiding about 40 students through the fundamentals of technological infrastructure."}