Publication Principled Design of Indexing Functions for Memory Coloring Stephan Dübler, Jana Hofmann, Boris Köpf, Stavros Volos 35th USENIX Security Symposium | August 2026 Project
Publication When does predictive inverse dynamics outperform behavior cloning? Lukas Schäfer, Pallavi Choudhury, Abdelhak Lemkhenter, Chris Lovett, Somjit Nath, Luis França, Matheus Ribeiro Furtado de Mendonça, Alex Lamb, Riashat Islam, Siddhartha Sen, John Langford, Katja Hofmann, Sergio Valcarcel Macua International Conference on Machine Learning Project
Publication Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games Somjit Nath, Abdelhak Lemkhenter, Pallavi Choudhury, Chris Lovett, Katja Hofmann, Sergio Valcarcel Macua, Lukas Schäfer IEEE Conference on Games Project
Publication Photonic Ising machines toward and beyond a million spins A. Aadhi, Nayem Al-Kayed, Tristan Austin, Charles St-Arnault, Nir Rotenberg, Hitesh Ballani, D. Plant, Edwin Ng, Yoshihisa Yamamoto, P. McMahon, B. Shastri July 2026 arXiv | July 2026
Publication Learning behavior accounts for background-related advantage in AI-assisted education Jingwei Yi, Yueqi Xie, Jiyan He, Rui Ye, Junming Huang, Bin Benjamin Zhu, Sean Rintel, Yueqi Xie, Xing Xie, Fangzhao Wu July 2026 arXiv | July 2026
Publication Dynamically Checked Deep Immutability in Python Fridtjof Stoldt, Sylvan Clebsch, Matthew Johnson, Matthew J. Parkinson, Tobias Wrigstad Proceedings of the ACM on Programming Languages | June 2026, Vol 10(PLDI): pp. 2623-2646 Project
Publication Position: Reasoning is a Learnable Rule-Based Process Rachel Lawrence, Jacqueline Maasch ICML 2026 | June 2026
Publication MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs Rui Wen, Mark Russinovich, Andrew Paverd, Jun Sakuma, Ahmed Salem May 2026 arXiv | May 2026
Publication Revisiting Transformer Layer Parameterization Through Causal Energy Minimization Jin Xu, Camille Couturier, Victor Ruhle, Saravan Rajmohan, James Hensman May 2026 arXiv | May 2026
Publication Position: Beyond Reasoning Zombies — AI Reasoning Requires Process Validity Rachel Lawrence, Jacqueline Maasch ICLM 2026 | May 2026 Preprint
Research