Author

Carsten Eickhoff

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Nov 2025

From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures

Upperological Signatures is presented for characterizing the structure of embedding spaces and finds that it outperforms individual metrics in downstream performance prediction and reveals novel insights into representational similarity that challenge the global claims of the Platonic Representation Hypothesis.

Florian Rottach, William Rudman, Bastian Rieck et al. · arXiv.org · 5 citations · ⚡1

#artificial intelligence Preprint Aug 2026

Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules

Across various benchmarks, it is shown that the representations learned by Mol-JEPA deliver strong performance, demonstrating the value of incorporating biochemical context through latent space prediction.

Florian Rottach, Sebastian Schieferdecker, William Rudman et al. · 0 citations