activity
20242026
collaborators

7 papers

cs.LG2026

How Post-Training Shapes Biological Reasoning Models

Lukas Fesser, Hanlin Zhang, Michelle M. Li +5

Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins. These models are bui…

cs.LG2026

A Unifying View of Attention Sinks: Two Algorithms, Two Solutions

Lukas Fesser, Mozes Jacobs, Thomas Fel +2

When attention concentrates on a single token, a sink, what is the model actually computing? Attention sinks are ubiquitous in softmax transformers, yet this shared visual signatur…

cs.AI2026

Evaluating Relational Reasoning in LLMs with REL

Lukas Fesser, Yasha Ektefaie, Ada Fang +2

Relational reasoning is the ability to infer relations that jointly bind multiple entities, attributes, or variables. This ability is central to scientific reasoning, but existing…

cs.CL2025

Multimodal Medical Code Tokenizer

Xiaorui Su, Shvat Messica, Yepeng Huang +5

Foundation models trained on patient electronic health records (EHRs) require tokenizing medical data into sequences of discrete vocabulary items. Existing tokenizers treat medical…

cs.LG2025

Performance Heterogeneity in Graph Neural Networks: Lessons for Architecture Design and Preprocessing

Lukas Fesser, Melanie Weber

Graph Neural Networks have emerged as the most popular architecture for graph-level learning, including graph classification and regression tasks, which frequently arise in areas s…

cs.LG2025

Enhancing the Utility of Higher-Order Information in Relational Learning

Raphael Pellegrin, Lukas Fesser, Melanie Weber

Higher-order information is crucial for relational learning in many domains where relationships extend beyond pairwise interactions. Hypergraphs provide a natural framework for mod…