Dor Tsur — accepted AI-conference papers

2025

HeavyWater and SimplexWater: Distortion-free LLM Watermarks for Low-Entropy Distributions

Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun, Sajani Vithana, Hsiang Hsu, Chun-Fu Chen +2

NeurIPS 2025poster

Large language model (LLM) watermarks enable authentication of text provenance, curb misuse of machine-generated text, and promote trust in AI systems. Current watermarks operate by changing the next-token predictions output by an LLM. The updated (i.e., watermarked) predictions depend on random si…

Cited by 0 Source ↗Scholar ↗

2023

Max-Sliced Mutual Information

Dor Tsur, Ziv Goldfeld, Kristjan Greenewald

NeurIPS 2023poster

Quantifying dependence between high-dimensional random variables is central to statistical learning and inference. Two classical methods are canonical correlation analysis (CCA), which identifies maximally correlated projected versions of the original variables, and Shannon's mutual information, whi…

Cited by 11 Source ↗PDF ↗Scholar ↗