Prasanna Mayilvahanan

I'm a fourth-year Ph.D. student at the Max Planck Institute for Intelligent Systems, Germany, and currently a Research Intern at Cohere working on exploration methods for LLM reasoning. In summer 2024, I spent time at Apple MLR as a Research Intern. Prior to this, I completed my master's studies at USI Lugano / ETH Zurich, and my bachelor's at IIT Guwahati.

Email  /  CV  /  Blog  /  Scholar  /  Twitter  /  Github

Research

My research spans benchmarking LLM reasoning capabilities, robustness of LLMs and VLMs, and foundations of representation learning. I am particularly interested in developing methods that enable models to discover patterns 'beyond their training distribution.' Currently, my focus is on exploration-driven RL approaches and methodologies that enhance generalization. Selected papers are highlighted.

MATH-B provides a diagnostic tool to distinguish whether post-training methods merely sharpen existing reasoning modes or genuinely discover novel solution paths beyond base model reach.

We find that two substantially different training setups—differing in architectures, tokenizers, optimizers, etc.—when trained on the same data and achieving identical training losses, consistently yield matching downstream performance across diverse tasks.

CLIP's high performance on style-centric domain shifts is significantly influenced by the presence of such images in its training set.

CLIP's ability to generalize to standard OOD benchmarks does not mainly stem from exact duplicates and near-duplicates in its training dataset.

We introduce a theoretical framework to analyze compositional generalization of neural networks within the regression setting.

We provide a neural network-based representation learning and clustering method for multi-omics data integration.

* denotes equal contribution
Template from Jon Barron's website.