Head of Google Translate Research
Mountain View, CA
Joined April 2012
- Tweets320
- Following214
- Followers1.3K
- Likes1K
Pinned Tweet
This release represents a huge team effort. So proud of this team! It's a joy to work alongside such brilliant people, and I can't wait to see how the research community uses @TranslateGemma in the future!
#AI #Gemma3
🗣 Introducing TranslateGemma, our new collection of open translation models built on Gemma 3.
The model is available in 4B, 12B, and 27B parameter sizes, and furthers communication across languages, no matter what device you own. blog.google/innovation-and-a…
I'll be at #COLM2026 tomorrow morning and all day Friday. Drop me a line if you're around and want to grab a coffee!
Markus Freitag retweeted
Very excited to announce Gemini 4 Argon! It delivers frontier performance across coding, knowledge work and cyber defense capabilities. The model is well-rounded and has great writing quality. The team has been hard at work producing this and we've all enjoyed using it everyday.
Lots of discussion out there about our next model(!), so I wanted to give an early look as soon as possible. Introducing Gemini 4 Argon!
It shows frontier performance in complex workflows, cyber defense and software engineering. Teams are using it extensively at Google, from coding to quantum computing, great feedback.
Here’s a look at the benchmarks:
Markus Freitag retweeted
I'm on the faculty job market for Fall 2027 assistant professorship. I work on the science of AI/NLP evaluation, which is currently undergoing a crisis:
Markus Freitag retweeted
We were asking one question a year ago: "Can we trust LLMs to build and grade their own benchmarks"? We tested frontier models on automated LLM benchmarking. The result? Every single model ranks itself #1 on benchmarks it generates (arxiv.org/abs/2509.26600). Our work has been accepted to EMNLP 2026 Main!
Markus Freitag retweeted
Happy to share CollabEval, recent(-ish) work from @GoogleDeepMind and @GoogleResearch that can be used to improve the statistical efficiency of model evaluation by exploiting correlations between historical evals of different models on the same tasks.
arxiv.org/pdf/2607.05046
Markus Freitag retweeted
🎓Completed a PhD on Machine Translation, multilingual, or cross-lingual NLP?
Nominate a standout thesis (or your own!) for the AMTA Best Thesis Award. Winner gets $1000, an invited talk at #AMTA2026 & more.
🗓️ Deadline: 15 May 2026
ℹ️Info: amtaweb.org/amta-2026-first-…
#MT #NLP #PhD
Markus Freitag retweeted
Announcing TranslateGemma, a new collection of open translation models built on Gemma 3. Learn more 👇
Markus Freitag retweeted
Check out TowerVision, a multilingual multicultural VLM powered by the @sardine_lab_it. Great work led by @Guilherme_PT1 and @psanfernandes! Bonus: TowerVideo, kudos to @Saul_Santos1997!
This project is the result of an amazing collaboration between researchers:
Authored by: @Guilherme_PT1 @psanfernandes @Saul_Santos1997 @SonalSannigrahi @ManosZaranis @nunonmg @amin_farajian @PierreColombo6 @gneubig @andre_t_martins
Markus Freitag retweeted
Every month, people use Google to translate around 1 trillion words. Today, we’re introducing a new AI-powered live translation experience in the Google Translate app, plus a new beta feature to help you practice new languages. Rolling out now on iOS + Android.
@_danieldeutsch @yixiao_song @ebriakou @caswell_isaac @marafinkels Rebecca Galor @JurikJuraska @gezakovacs Alison Lui @RicardoRei7 @jasonriesa @shrutirij @prk_riley @esalesk Firas Trabelsi Stephanie Winkler @BZhangGo @mykocyigit @ColinCherry Jiaming Luo @lilyhzhang Hamid Dadkhahi
📄Learning from others' mistakes: Finetuning machine translation models with span-level error annotations
lnkd.in/gMrkUnRe
📄 From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set
lnkd.in/gC7ZgwWm
📄 Overestimation in LLM Evaluation... Impact on Machine Translation
lnkd.in/gXWCh53C
And a quick highlight from #ICML2025 (presented in Vancouver 2 weeks ago!) where we shared these impactful papers:
🗓️ Mon, July 28 | 18:00-19:30
WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects
lnkd.in/gip_sWuC
🗓️ Tue, July 29 | 16:00-17:30 (virtual)
Enhancing Human Evaluation in Machine Translation with Comparative Judgement
lnkd.in/gt7V4GSz
Our Google Translate team is bringing a strong presence to #ACL2025 in Vienna this week! 🇦🇹 My group is excited to present several of our latest papers. 👇 Don't miss them!
Markus Freitag retweeted
MT metrics excel at evaluating sentence translations, but struggle with complex texts
We introduce *TREQA* a framework to assess how translations preserve key info by using LLMs to generate & answer questions about them
arxiv.org/abs/2504.07583
(co-lead @swetaagrawal20)
1/15
Markus Freitag retweeted
.@Google and @imperialcollege researchers argue that translation quality can’t be captured 🛑 by a single metric and propose evaluating #AI #translation systems 🤖 on an accuracy-naturalness plane.
#xl8 #t9n #Google @GoogleAI @markuseful
slator.com/google-calls-for-…
Markus Freitag retweeted
😼SMOL DATA ALERT! 😼Anouncing SMOL, a professionally-translated dataset for 115 very low-resource languages! Paper: arxiv.org/pdf/2502.12301
Huggingface: huggingface.co/datasets/goog…
