Doctoral Researcher
Friedrich-Schiller-Universität Jena
About
I am a PhD student in AI for science, working with Dr. Kevin Maik Jablonka. I'm building machine learning systems to speed up scientific research, and I love projects that involve both research and building the tooling that enables and accelerates that research. Lately, I’ve been analyzing general-purpose AI models/systems to understand their limitations in scientific applications—where they fail—and interpreting them to uncover why they fail. My goal is to use these insights to design AI systems that aren’t just impressive on benchmarks but truly impactful for advancing science and research.
February 2026
I joined Lila Sciences as an AI resident in Boston from February to June 2026.
May 2025
I contributed to DeepMind, evaluating scientific reasoning in Gemini models. Read more about my project.
arXiv 2026
Martiño Ríos-García, Nawaf Alampara, Chandan Gupta, Ishita Mandal, Sahil Mannan, Amir Mohammad Aghajani, N. M. Anoop Krishnan, Kevin Maik Jablonka
25,000 AI scientist experiments reveal that LLMs ignore gathered evidence, never update beliefs, and harness has less impact compared to the underlying model.
Chemical Reviews 2026
Nawaf Alampara, Anagha Aneesh, Martiño Ríos-García, Adrian Mirza, Mara Schilling-Wilhelmi, ..., Kevin Maik Jablonka
Theory, concepts, application and thought behind "general purpose models" for chemical sciences.
arXiv 2026
Martiño Ríos-García, Nawaf Alampara, Kevin Maik Jablonka
The meaning of inputs can change how well language models perform the same counting task.
Nature Computational Science 2026
NeurIPS AI4Mat 2024 oral
Nawaf Alampara, Santiago Miret, Kevin Maik Jablonka
Using MatText, we found that language models struggle to learn the geometric information needed for materials property prediction.
Nature Computational Science 2025
⭐ Neurips AI4Mat
Nawaf Alampara, ..,Kevin Maik Jablonka
Multimodal benchmark for chemistry/materials science for AI with ablations to interpret the limitations
Advisor: Dr. Kevin Maik Jablonka
Post-training methods for scientific language models
Evaluated scientific reasoning in Gemini models
Dataset curation | Benchmarking
Material simulation using geometric deep learning models | Software development
Real-time video analytics | Computer vision
PhD Machine Learning for Science
Advisor: Dr. Kevin Maik Jablonka
MSc Energy Science
Advisor: Prof. K R Balasubramaniam
Thesis: Defects and Dopants in Cu₂O - DFT study