We created SynthID, a robust digital watermarking technology to tag & identify AI-generated content. Now we’re open-sourcing SynthID-Text so developers can use it to embed & detect watermarks in text outputs from their own LLMs. Published today in nature nature.com/articles/s4158…

📢 We are excited to announce our 7th *virtual* mentoring workshop which will be held on November 13 - 14, 2024. Registration (docs.google.com/forms/d/e/1FAI…) is open and free for all. See the full schedule at let-all.com/fall24.html. #MLTheory [1/4]

I had the privilege of being interviewed by the marvelous and unique Steve Strogatz on the podcast "The Joy of Why." We talked about how AI is changing the science of prediction. Links are below: open.spotify.com/episode/50Y4M6… quantamagazine.org/tag/the-joy-of… podcasts.apple.com/us/podcast/the…

Debiasing Watermarks for Large Language Models via Maximal Coupling ift.tt/0LyVA1M

Robust Detection of Watermarks for Large Language Models Under Human Edits ift.tt/FSnM5Au

Large Concept Models: Language Modeling in a Sentence Representation Space This new paper from Meta introduces a very interesting, novel approach to language modeling. Rather than doing prediction of the next subword token, focus on generating the next concept, which is

An Overview of Large Language Models for Statisticians ift.tt/Y2vcz4u

[1/n] New work [JSKZ25] w/ Jikai Jin, Vasilis Syrgkanis, Sham Kakade. We introduce new formulations and tools for evaluating language model capabilities, which help explain recent observations of post-training behaviors of Qwen-series models — there is a sensitive causal link

Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts ift.tt/4cTUdqm