collaborators

15 papers

cs.LG2026

MatBind: A Shared Embedding Space for Multimodal Materials Characterization

Le Yang, Anoop K. Chandran, Jona Östreicher +8

Fully characterizing a crystalline material requires integrating heterogeneous data sources -- atomic structures, diffraction patterns, electronic density of states, and natural la…

cs.LG2026

Reducing cross-sample prediction churn in scientific machine learning

Gordan Prastalo, Kevin Maik Jablonka

Scientific machine learning reports predictive performance. It does not report whether the same prediction would survive a different draw of training data. Across chemistry ben…

cs.AI2026

Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery

Harshit Bisht, Vinay Kumar, Kevin Maik Jablonka +2

A growing body of work pursues AI scientists capable of end-to-end autonomous scientific discovery. This position paper argues that although they already function as co-scientists,…

cs.AI2026

AI scientists produce results without reasoning scientifically

Martiño Ríos-García, Nawaf Alampara, Chandan Gupta +5

Large language model (LLM)-based systems are increasingly deployed to conduct scientific research autonomously, yet whether their reasoning adheres to the epistemic norms that make…

physics.chem-ph2026

Clever Materials: When Models Identify Good Materials for the Wrong Reasons

Kevin Maik Jablonka

Machine learning can accelerate materials discovery. Models perform impressively on many benchmarks. However, strong benchmark performance does not imply that a model learned chemi…

physics.chem-ph2026

Beyond Learning on Molecules by Weakly Supervising on Molecules

Gordan Prastalo, Kevin Maik Jablonka

Molecular representations are inherently task-dependent, yet most pre-trained molecular encoders are not. Task conditioning promises representations that reorganize based on task d…