Research Scientist at @GoogleDeepMind
Joined December 2017
- Tweets 57
- Following 76
- Followers 292
- Likes 155
Photos and videos
Rahma retweeted
22 May 2025
Writing a STRONGLY WORDED LETTER with Gemini Diffusion and its Instant Edit tab
1
7
28
2,534
Rahma retweeted
21 May 2025
The Future of Development: Gemini Diffusion
19
89
952
129,749
Rahma retweeted
20 May 2025
Today we introduced Gemini Diffusion⚡️ (& DeepThink, Veo3, Imagen4, 2.5 updates...).
It's been a dream of mine to remove the need for "left to right" text generation. It's so fast, that we had to *slow down* the video during the presentation.
deepmind.google/models/gemin…
32
94
764
79,803
Rahma retweeted
20 May 2025
Such a privilege to work on Gemini Diffusion with an amazing team! From a small research project to launching at I/O - we've got unstoppable aura 🚀
Welcome to the era of live vibe coding ⚡️
3
8
39
8,140
Rahma retweeted
20 May 2025
🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀
Very excited to be able to share what I've been working on for the past little while with our amazing small team @GoogleDeepMind.
20 May 2025
We’ve developed Gemini Diffusion: our state-of-the-art text diffusion model.
Instead of predicting text directly, it learns to generate outputs by refining noise, step-by-step. This helps it excel at coding and math, where it can iterate over solutions quickly. #GoogleIO
23
41
426
43,469
Rahma retweeted
20 May 2025
Well now, the prospect of using this 'Gemini Diffusion' contraption... frankly, it's a rather delightful thought altogether!
1
3
8
875
20 May 2025
It's been an incredible experience working on Gemini Diffusion. So much pride in what we've accomplished bringing this from a small research project to an I/O launch
20 May 2025
We’ve developed Gemini Diffusion: our state-of-the-art text diffusion model.
Instead of predicting text directly, it learns to generate outputs by refining noise, step-by-step. This helps it excel at coding and math, where it can iterate over solutions quickly. #GoogleIO
2
13
103
12,886
Rahma retweeted
20 May 2025
We’ve developed Gemini Diffusion: our state-of-the-art text diffusion model.
Instead of predicting text directly, it learns to generate outputs by refining noise, step-by-step. This helps it excel at coding and math, where it can iterate over solutions quickly. #GoogleIO
91
640
4,494
1,298,273
Rahma retweeted
20 May 2025
1000 words per second! ⚡
We just unleashed Gemini Diffusion at #GoogleIO! 🚀
Awesome being part of the team that took this from a small research project all the way to I/O @GoogleDeepMind 🪐
20 May 2025
We’ve developed Gemini Diffusion: our state-of-the-art text diffusion model.
Instead of predicting text directly, it learns to generate outputs by refining noise, step-by-step. This helps it excel at coding and math, where it can iterate over solutions quickly. #GoogleIO
6
31
136
9,242
Rahma retweeted
15 Feb 2024
In December we began the Gemini Era, and we’ve continued to make relentless progress since. Today we’re thrilled to introduce the next generation: Gemini 1.5 - hugely enhanced performance, highly efficient architecture & long-context length breakthrough
blog.google/technology/ai/go…
56
194
1,393
596,538
Rahma retweeted
9 Feb 2024
Another tour de force by @ibalazevic, and a thoroughly enjoyable new collaboration with @YugeTen, @pinelopip3, @Rahma_Chaa, and @skandakoppula
You can find the paper here arxiv.org/abs/2402.05861
3
5
16
1,207
Rahma retweeted
9 Feb 2024
Humans and animals reason about events spanning days, weeks, and years, yet current CV systems live largely in the present.
Introducing Memory-Consolidated ViT, whose context extends far into the past and sets a new SOTA in long-video understanding with a 10x smaller model
5
26
167
36,481
Rahma retweeted
9 Sep 2021
Read more in a BlackBox EMNLP 2021 paper by @Rahma_Chaa , @robdessi, and myself arxiv.org/abs/2107.01366
2
5
Rahma retweeted
9 Sep 2021
Transformer seq2seq models enjoy epic practical success, however, they miserably fail on SCAN data that probes for compositional reasoning.. - wait! compositionality is a cornerstone of the language. Is there a contradiction? Is work on SCAN compositionality even useful then? 🧶\
1
20
95
Rahma retweeted
28 Mar 2021
Wanted: Phd candidate Université de Paris 2021
Meaning-based approach to locality constraints
Advisors: Anne Abeillé, Barbara Hemforth, Edward Gibson
Please apply and retweet!
llf.cnrs.fr/en/node/6836
47
50
Rahma retweeted
24 Mar 2021
The way people use words to describe colors is remarkably consistent across thousands of languages. New Facebook AI research published in the “Proceedings of the National Academy of Sciences” shows that cutting-edge AI systems name colors in a similar way: ai.facebook.com/blog/ai-name…
1
39
158
18 Mar 2021
We demonstrate next that the nature of the emergent systems depends on communication being discrete. Our study suggests that efficient semantic categorization is a general property of discrete communication systems, not limited to human language.
18 Mar 2021
I am very proud about our work with @n0mad_0, Emmanuel and Marco accepted at PNAS.
2
9
18 Mar 2021
We show that artificial neural networks trained to play a discrimination game develop emergent communication systems whose distribution on the accuracy/complexity plane closely matches that of human languages.
18 Mar 2021
I am very proud about our work with @n0mad_0, Emmanuel and Marco accepted at PNAS.
1
8
18 Mar 2021
I am very proud about our work with @n0mad_0, Emmanuel and Marco accepted at PNAS.
18 Mar 2021
Communicating artificial neural networks develop efficient color-naming systems pnas.org/content/118/12/e201…
1
4
23
Rahma retweeted
4 Mar 2021
The latest generation of adversarial image attacks is, uh, somewhat simpler to carry out openai.com/blog/multimodal-n…
157
4,756
15,546