Anian Ruoss
Publications by Year
Research Areas
Adversarial Robustness in Machine Learning, Ethics and Social Impacts of AI, Topic Modeling, Natural Language Processing Techniques, Explainable Artificial Intelligence (XAI)
Most-Cited Works
- → Neural Networks and the Chomsky Hierarchy(2022)45 cited
- → Learning Certified Individually Fair Representations(2020)27 cited
- → Language Modeling Is Compression(2023)26 cited
- → Randomized Positional Encodings Boost Length Generalization of Transformers(2023)15 cited
- → Efficient Certification of Spatial Robustness(2021)14 cited
- → Evaluating Frontier Models for Dangerous Capabilities(2024)9 cited
- → Amortized Planning with Large-Scale Transformers: A Case Study on Chess(2024)8 cited
- → Latent Space Smoothing for Individually Fair Representations(2022)7 cited
- Fair Normalizing Flows(2021)