today local_bar

Hsiang Hsu

Researcher, JP Morgan & Chase Bank

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

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

#1406 · Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun, Sajani Vithana, Hsiang Hsu, Chun-Fu Chen, Haim H. Permuter, Flavio Calmon

Using coding theory and heavy tails to design powerful watermarks with zero distortion.

The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples

#1302 · Hsiang Hsu, Pradeep Niroula, Zichang He, Ivan Brugere, Freddy Lecue, Chun-Fu Chen