Profiles2022-2026
Yan Scholten
Department of Computer Science & Munich Data Science Institute Technical University of Munich
7Papers
0Last author
7Unique co-authors
5First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers7
- Sampling-aware Adversarial Attacks Against Large Language ModelsAuthor 2 of 4ICLR 2026 · 9 citations
- Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMsAuthor 1 of 4ICLR 2026 · 8 citations
- A Probabilistic Perspective on Unlearning and Alignment for Large Language ModelsAuthor 1 of 3ICLR 2025
- Provably Reliable Conformal Prediction Sets in the Presence of Data PoisoningAuthor 1 of 2ICLR 2025
- Hierarchical Randomized SmoothingAuthor 1 of 4NeurIPS 2023 · 14 citations
- (Provable) Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and MoreAuthor 2 of 3NeurIPS 2023 · 5 citations
- Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural NetworksAuthor 1 of 5NeurIPS 2022 · 20 citations
