← Search

Kuheli Pratihar

2 accepted papers

2026

Catch-22: On the Fundamental Tradeoff Between Detectability and Robustness in LLM Watermarking

ICML 2026spotlight

Large language models generate text through probabilistic token sampling, a mechanism increasingly leveraged for inference-time watermarking to verify AI-generated content. We present an information-theoretic framework that characterizes the trade-off between robustness to text editing and detectabi…

Cited by 0SourceScholar
2025

Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders

ICML 2025poster

Variational Autoencoders (VAEs), a class of latent-variable generative models, have seen extensive use in high-fidelity synthesis tasks, yet their loss landscape remains poorly understood. Prior theoretical works on VAE loss analysis have focused on their latent-space representational capabilities,…

Cited by 0SourcePDFScholar