Jason Riesa
@jasonriesa
i18n / Multilinguality Research @GoogleDeepMind
🚀 Join the Gemini Multilinguality team @GoogleDeepMind 🌐 We’re looking for researchers passionate about making LLMs helpful for all. Dramatically improve model quality, coverage, and cultural relevance across hundreds of languages. #NLProc #MultilingualAI #i18n #LLMs…
Introducing ECLeKTic, a new benchmark for Evaluating Cross-Lingual Knowledge Transfer in LLMs. It uses a closed-book QA task, where models must rely on internal knowledge to answer questions based on information captured only in a single language. More →goo.gle/3Y5TqvZ
1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on…
1/ Today we are releasing Gemini 2.5 Pro Experimental, our newest Gemini model with integrated “thinking” and significant performance gains. Very proud of the whole team! 🧵
Nebula
🚨New machine translation dataset alert! 🚨We expanded the language coverage of WMT24 from 9 to 55 en->xx language pairs by collecting new reference translations for 46 languages in a dataset called WMT24++ Paper: arxiv.org/abs/2502.12404… Data: huggingface.co/datasets/googl…
Gemini 2.0 Flash is here! 🎊 We're quite excited about this model. It's better than Gemini 1.5 Pro on most benchmarks, but comparable in speed and latency to Gemini 1.5 Flash. It has multilingual native audio output, native image output, native tool use, and a new multimodal…
Massive News from Chatbot Arena🔥 @GoogleDeepMind's latest Gemini (Exp 1114), tested with 6K+ community votes over the past week, now ranks joint #1 overall with an impressive 40+ score leap — matching 4o-latest in and surpassing o1-preview! It also claims #1 on Vision…
gemini-exp-1114…. available in Google AI Studio right now, enjoy : ) aistudio.google.com
Exciting opportunity in the Languages team at @GoogleDeepMind India to advance LLM frontiers and bring their benefits to a lot more people! Get in touch for any queries. I shall also be at @aclmeeting next week, happy to chat in person. boards.greenhouse.io/deepmind/jobs/…
Never seen a competitive leaderboard that I didn't like 😀 Congrats to the Gemini team on ranking no.1 🏆 with our latest improved Gemini 1.5 Pro developer preview model, which you can try on AI studio now!
Exciting News from Chatbot Arena! @GoogleDeepMind's new Gemini 1.5 Pro (Experimental 0801) has been tested in Arena for the past week, gathering over 12K community votes. For the first time, Google Gemini has claimed the #1 spot, surpassing GPT-4o/Claude-3.5 with an impressive…
Exciting News from Chatbot Arena! @GoogleDeepMind's new Gemini 1.5 Pro (Experimental 0801) has been tested in Arena for the past week, gathering over 12K community votes. For the first time, Google Gemini has claimed the #1 spot, surpassing GPT-4o/Claude-3.5 with an impressive…
Today, we are making an experimental version (0801) of Gemini 1.5 Pro available for early testing and feedback in Google AI Studio and the Gemini API. Try it out and let us know what you think! aistudio.google.com
Gemini 1.5 Pro - A highly capable multimodal model with a 10M token context length Today we are releasing the first demonstrations of the capabilities of the Gemini 1.5 series, with the Gemini 1.5 Pro model. One of the key differentiators of this model is its incredibly long…
Is that speech English, Spanish, or Mandarin? 🕵️♂️ 🔊Super excited to share several works that improve language identification capabilities via both pre-training and fine-tuning. MuSeLI: Multimodal modeling for spoken language identification [ICASSP 2024] 📎…
I'm at #NeurIPS2023 today presenting MADLAD-400 with @BZhangGo and @adityakusupati at 5:15pm in Hall B1/B2 #314! Come by and chat w/ us about creating *massive* datasets, making sure they're not garbage, and multilingual LMs :D
Excited to announce MADLAD-400 - a 2.8T token web-domain dataset that covers 419 languages(!). Arxiv: arxiv.org/abs/2309.04662 Github: github.com/google-researc… 1/n
Our work on cross-lingual and multilingual attribution will be presented at #EMNLP2023 in Singapore! We have also released our dataset of ~10k 3-way annotations over 5 typologically diverse languages. Arxiv: arxiv.org/abs/2305.14332 Dataset: github.com/google-researc…
We all want accurate responses from our QA systems, and this need becomes especially vital when interacting with text in languages unfamiliar to us, rendering answer verification reliant on translation. This challenge is particularly felt by speakers of low-resource languages.
Thrilled to work with such a talented group of folks to bring the capabilities of LLMs and generative AI to more languages and locales, and into the hands of users around the world.
I’m very excited to share our work on Gemini today! Gemini is a family of multimodal models that demonstrate really strong capabilities across the image, audio, video, and text domains. Our most-capable model, Gemini Ultra, advances the state of the art in 30 of 32 benchmarks,…
Despite the fantastic progress we've seen recently in cross-lingual modeling, the best systems still make a lot of factual errors. To address this, here is our work on 🚨 Evaluating and Modeling Attribution for Cross-Lingual Question Answering 🚨 #1 Attribution Evaluation: Our…
With the rapid development of language technology, it’s important that as many languages as possible benefit from these technologies, so we’re sharing XTREME-UP, a benchmark for evaluating multilingual models. 📝goo.gle/xtreme-up-paper 💻github.com/google-researc… Read 🧵↓ (1/3)
Introducing Conditional Adapters (CoDA) from Google Research! Adaptation methods (e.g. Adapter and LoRA) can finetune LMs with minimal parameter updates, but their inference remains expensive. CoDA makes LMs faster to use, and works for three modalities! arxiv.org/abs/2304.04947