LLM Watermarking Resurfaces: Meta Researcher's Past Work Highlighted
antoine_chaffin · x · 2026-08-11
As the EU AI Act brings LLM output watermarking back into the spotlight, the author reflects on their past collaboration with Meta researcher Pierre Fernandez.
Having completed his PhD under notable scholars like Teddy Furon, Fernandez has worked extensively on watermarking various media at Meta. The author shares a slightly older but classic text watermarking paper, recommending it as a great entry point into the field.
More from Research
- DeepSeek's Recent Two Major Releases Leave Next Paper Direction a Mystery — teortaxesTex · 2026-08-11
- Luth-2 Released: Sets New SOTA for French Small Language Models — Unusual_Shoe2671 · 2026-08-11
- Open-Source SynthID-Text-Detector: Reference Implementation for AI Text Watermarking — jedisct1 · 2026-08-11
- Does LLM Watering Degrade Quality? Researcher's 10-Point FAQ Debunks Myths — jonasgeiping · 2026-08-11
- Tsinghua's Tianmouc Chip Featured on Nature Sensors: A Self-Supervised Framework to Overcome Real-World Visual Degradation — 机器之心 · 2026-08-11
- RUC & Ant Group's LLaDAMoEv2 Matches Qwen3 with 65% Pretraining Tokens — 机器之心 · 2026-08-11