Simon Ostermann, Daniil Gurgurov, Tanja Baeumel, Michael A. Hedderich, Sebastian Lapuschkin, Wojciech Samek, and Vera Schmitt. From Weights to Activations: Is Steering the Next Frontier of Adaptation? (Main)
Dan Shi, Zhuowen Han, Simon Ostermann, Renren Jin, Josef van Genabith, and Deyi Xiong. Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models. (Main)
Daniil Gurgurov, Yusser Al Ghussin, Tanja Baeumel, Cheng-Ting Chou, Patrick Schramowski, Marius Mosbach, Josef van Genabith, and Simon Ostermann. CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark. (Findings)
Cennet Oguz, Yasser Hamidullah, Josef van Genabith, and Simon Ostermann. DualFact+: A Multimodal Fact Verification Framework for Procedural Video Captioning. (Findings)
Glückwünsche an alle Autorinnen und Autoren!