2025 MIB: A Mechanistic Interpretability Benchmark Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fiotto-Kaufman, Tal Haklay, Michael Hanna, and 13 more authors In ICML, 2025 Website Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics Yaniv Nikankin, Anja Reusch, Aaron Mueller, and Yonatan Belinkov In ICLR, 2025 Code Website 2023 Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses Gon Buzaglo, Niv Haim, Gilad Yehudai, Gal Vardi, Yakir Oz, Yaniv Nikankin, and Michal Irani In NeurIPS, 2023 SinFusion: Training Diffusion Models on a Single Image or Video Yaniv Nikankin, Niv Haim, and Michal Irani In ICML, 2023 Code Website