Arad, Dana

1. SAEs Are Good for Steering -- If You Select the Right Features
   2025/05/26 by Dana Arad, Aaron Mueller, Arad, Dana +3 · 1 voice · 17 citations
   Engineering · #cs.LG #cs.AI #cs.CL
2. ReFACT: Updating Text-to-Image Models by Editing the Text Encoder
   2023/06/01 by Arad, Dana, Orgad, Hadas, Belinkov, Yonatan · 5 citations
   #68T50 #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #I.2.7
3. MIB: A Mechanistic Interpretability Benchmark
   2025/04/17 by Aaron Mueller, Atticus Geiger, Mueller, Aaron +45 · 1 voice · 6 citations
   Computer Science · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #Topic Modeling #cs.AI #cs.CL #cs.LG
4. Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
   2025/06/10 by Nikankin, Yaniv, Arad, Dana, Gandelsman, Yossi +1 · 4 citations
   #68T5 #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7