Constantin Venhoff

According to our database, Constantin Venhoff authored at least 8 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Base Models Know How to Reason, Thinking Models Learn When.

Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda

CoRR, October, 2025

Towards Mechanistic Defenses Against Typographic Attacks in CLIP.

Lorenz Hufe, Constantin Venhoff, Maximilian Dreyer, Sebastian Lapuschkin, Wojciech Samek

CoRR, August, 2025

Reasoning-Finetuning Repurposes Latent Representations in Base Models.

Jake Ward, Chuqiao Lin, Constantin Venhoff, Neel Nanda

CoRR, July, 2025

Understanding Reasoning in Thinking Language Models via Steering Vectors.

Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda

CoRR, June, 2025

How Visual Representations Map to Language Feature Space in Multimodal LLMs.

Constantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip Torr, Neel Nanda

CoRR, June, 2025

Mixture of Experts Made Intrinsically Interpretable.

Xingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schröder de Witt, Puneet K. Dokania, Adel Bibi, Philip Torr

CoRR, March, 2025

2024

SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders.

Constantin Venhoff, Anisoara Calinescu, Philip Torr, Christian Schröder de Witt

CoRR, 2024

2023

Leveraging Natural Language Processing for a Consistency Checking Toolchain of Automotive Requirements.

Vincent Bertram, Hendrik Kausch, Evgeny Kusmenko, Haron Nqiri, Bernhard Rumpe, Constantin Venhoff

Proceedings of the 31st IEEE International Requirements Engineering Conference, 2023