Venhoff, Constantin

3 publications

ICML 2025 Mixture of Experts Made Intrinsically Interpretable Xingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schroeder De Witt, Puneet K. Dokania, Adel Bibi, Philip Torr

NeurIPS 2025 Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval Constantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip Torr, Neel Nanda

ICLRW 2025 Understanding Reasoning in Thinking Language Models via Steering Vectors Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda