2 papers
cs.CL2025
Compute-Accuracy Pareto Frontiers for Open-Source Reasoning Large Language Models
Ãkos Prucs, Nara Csutora, Mátyás Antal +1
Large Language Models (LLMs) are demonstrating rapid improvements on complex reasoning benchmarks, particularly when allowed to utilize intermediate reasoning steps before convergi…
cs.LG2025
Circuits, Features, and Heuristics in Molecular Transformers
Kristof Varadi, Mark Marosi, Peter Antal
Transformers generate valid and diverse chemical structures, but little is known about the mechanisms that enable these models to capture the rules of molecular representation. We…