Roman Castagné @RomCast_
Member of Technical Staff @cohere, previously @InriaParisNLP @Inria, Ecole des Ponts ParisTech, MVA at ENS Paris-Saclay, intern at @NaverLabsEurope romancast.github.io Joined March 2020-
Tweets40
-
Followers162
-
Following562
-
Likes1K
Introducing Cohere's first open-source coding model: North Mini Code Small & efficient, designed for agentic performance and built for community input.
Introducing: Cohere Command A+ We’ve created our most powerful LLM yet, optimized it to run on as little hardware as possible, and released it open-source for all.
Introducing: Cohere Transcribe – a new state-of-the-art in open source speech recognition.
Introducing Command A Reasoning, our most advanced model for enterprise reasoning tasks.
Introducing Command A Vision, a state-of-the-art generative model that excels across multimodal image capabilities that matter for enterprises!
@awnihannun @johnowhitaker Same thing for Llamba actually, they use the MLP weights, embeddings and layernorms from the teacher.
🚀 New Paper Alert! 🚀 We introduce Q-Filters, a training-free method for efficient KV Cache compression! It is compatible with FlashAttention and can compress along generation which is particularly useful for reasoning models ⚡ ⬇️R1-Distill-Llama-8B with 128 KV pairs ⬇️ 🧵
Today, we’re excited to release Command R7B, the smallest, fastest, and final model in the R series. It’s a powerhouse with a minimal footprint.
Introducing Command R7B: the smallest, fastest, and final model in our R series of enterprise-focused LLMs! It delivers a powerful combination of state-of-the-art performance in its class and efficiency to lower the cost of building AI applications. cohere.com/blog/command-r…
Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier 🌿 Today, we release a technical report with extended evaluation for Aya Expanse, our new generation of 8B and 32B parameters multilingual language models 🌎
We’re excited to announce our Series D financing to accelerate growth, expand our team, & develop our next class of frontier, enterprise-grade, data privacy-focused AI technology. We’re bringing highly scalable and secure AI solutions to global enterprises wherever their data is and in whatever language they speak.
@cohere just shipped json schema sampling! Now not only can you guarantee that the model returns valid json, you can actually ensure it returns json with a specific format! Big win for people actually building with LLMs :) dashboard.cohere.com/playground/chat
Exciting news - the latest Arena result are out! @cohere's Command R+ has climbed to the 6th spot, matching GPT-4-0314 level by 13K+ human votes! It's undoubtedly the **best** open model on the leaderboard now🔥 Big congrats to @cohere's incredible work & valuable contribution to the open community! More exciting updates: - Qwen1.5-32B-Chat almost top-10 - Gemma-1.1-7B-it shows great improvement (1044 -> 1088, on par with Llama-2-70b) - Starling-7B-Beta still the best 7B with over 13K votes!
Hot damn, @cohere @cohereForAI is really bringing it
⌘R+ Welcoming Command R+, our latest model focused on scalability, RAG, and Tool Use. Like last time, we're releasing the weights for research use, we hope they're useful to everyone! txt.cohere.com/command-r-plus…
One subtlety worth mentioning is how significant the tokenizer is to the cost to use models in non-english languages. Our tokenizer is meaningfully better than others at the 9 non-English languages, achieving up to a 2x effective cost reduction to use.
Today, we’re introducing Command R+: a state-of-the-art RAG-optimized LLM designed to tackle enterprise-grade workloads and speak the languages of global business. Our R-series model family is now available on Microsoft Azure, and coming soon to additional cloud providers.
Announcing C4AI Command R+ open weights, a state-of-the-art 104B LLM with RAG, tooling and multilingual in 10 languages. This release builds on our 35B and is a part of our commitment to make AI breakthroughs accessible to the research community. 🎉 huggingface.co/CohereForAI/c4…
⌘R+ Welcoming Command R+, our latest model focused on scalability, RAG, and Tool Use. Like last time, we're releasing the weights for research use, we hope they're useful to everyone! txt.cohere.com/command-r-plus…
Here are the weights: huggingface.co/CohereForAI/c4…
Viraat Aryabumi @viraataryabumi
742 Followers 482 Following multimodal @cohere | ex-scholar @cohere_labs | ex-MLE @amazondevscot Opinions are my own
faizan khan @faizan10114
980 Followers 3K Following https://t.co/JhJCxe3bHV (get more agents to use your product) 24/7 support https://t.co/rV4UMvGpNL @sirdocsalot
J Rosser ✈️ ICML @jrosseruk
1K Followers 2K Following Research Associate with @NeelNanda5 @ Adecco supporting @GoogleDeepMind | ex-@cohere | DPhil @UniofOxford @j_foerst
Hossam Amer @Hossam_Amer12
328 Followers 650 Following Hossam Amer (7@S7@S), a person that has passed and still passing thru a lot of things to be the way he is. He is ambitious, lucky, likes ppl, basketball, BLUE.
Ahmet Üstün @ahmetustun89
2K Followers 674 Following Code Agents Lead @cohere. Previously Research Scientist @Cohere_Labs, @GroNlp, @naverlabseurope.
Simon Lehnerer @SimonLehnerer_
56 Followers 300 Following Pretraining @Cohere. Previously ML @Apple, ML @UCL, Physics @ETH_en.
Konstantin Dobler @konstantdobler
308 Followers 430 Following ELLIS PhD student @hpi_de, prev intern @apple @instadeepai @sap | Multilingual LLMs, tokenization, embeddings
Smuethars @SmuetharsWLH
85 Followers 281 Following
Ashima Suvarna🌻 @suvarna_ashima
530 Followers 879 Following Phd-ing @UCLA | Research Intern @MSFTResearch | @Deepmind Scholar '21 | Mitacs Scholar '19
Jin Schofield @jinschofield
120 Followers 633 Following Incoming CS PhD @ NYU Courant | Research Fellow @ CBAI/MIT, Princeton RL | prev. Princeton undergrad, ML Intern @ ACS, Diffusion @ Caltech, Research @ Oxford
Kyle Duffy @kyduffy
165 Followers 254 Following do art with science vision ML @cohere | prev NLP @uniofoxford
Mohamed Malhou @MalhouMohamed
50 Followers 441 Following PhD Student at @AIatMeta and @Sorbonne_Univ_, co-supervised by Ludovic Perret, @f_charton and @KristinLauter. AI for Math
Arnaud Stiegler @ArnaudStiegler
296 Followers 344 Following RL environments and reasoning at ReflectionAI
Serena Hills @HillsSeren78850
144 Followers 5K Following
Diana Abagyan @dianaabagyan
353 Followers 155 Following Pretraining @cohere | former Research Scholar @Cohere_Labs
Yi-Chern @yichern_tan
257 Followers 272 Following lead, post-training @cohere. previously @Waymo @Facebook @Yale. 🇸🇬
Saurabh Dash @TheyCallMeMr_
632 Followers 692 Following Bottomless pit supervisor. ML @CohereAI , PhD Student @GeorgiaTech. Previously @Apple, @IITkgp. https://t.co/yZLkUsiZ7P. Opinions expressed are my own
gabedaramola @gabedaramola
0 Followers 7K Following
michelangelo13 @micheleangelo13
2K Followers 8K Following
Jaap Jumelet @JumeletJ
743 Followers 409 Following Post-doc with @AriannaBisazza in Groningen PhD with Jelle Zuidema at the ILLC, UvA Doing computational linguistics in the age of LLMs
Nédey Oriane @NedeyOriane
7 Followers 108 Following
Shashidhar Reddy Java... @im_Shashi16
47 Followers 672 Following PhD in CS, Stevens Institute of Technology, Master's Grad, UMass Amherst, Currently working on AI for research and Interpretable AI.
Sylvie Shi @sylvieshi00
729 Followers 364 Following llm pretraining @cohere. previously led reranking at cohere
Nathan Grinsztajn @ N... @NGrinsztajn
396 Followers 615 Following Agentic @MistralAI, ex: @cohere, InstaDeep | PhD in reinforcement learning for combinatorial optimization @InriaScool
Irem Ergün @irombie
2K Followers 561 Following •mle @cohere; LLM posttraining •i write code&songs&stories •🇹🇷🇬🇧 tweets •proud Bilkenter •chasing legacy✨ •views are mine, not my employer's. rt≠endorsement
Maximilian Mozes @maximilianmozes
331 Followers 619 Following Staff Research Scientist @cohere. PhD @UCL/@ucl_nlp. Previously: @GoogleAI/@SpotifyResearch. He/Him.
Yannis Flet-Berliac @yfletberliac
788 Followers 956 Following ai research scientist @cohere. past: postdoc @stanford / cs phd @inria / associate program chair @icmlconf
John Dang @johnamqdang
1K Followers 1K Following AI Researcher, Founding Team at @adaption_ai | Prev @Cohere_Labs @Cohere | LLM Post-Training, RL, Reasoning, Multimodality, Multilinguality
V. Gurucharan @DrVGCharan
425 Followers 7K Following Chief AI Officer | NLP Research | AI Governance | PhD (String Theory) | Geopolitics
Ekagra Ranjan @EkagraRanjan
218 Followers 405 Following LLM Inference & Efficiency @cohere • Ex-@Microsoft • Open Source @PyTorch • Intern @IiscNLP (MALL Lab, IISc), @IITKgp • B. Tech @IITGuwahati • Machine Learning
Laurie Burchell @very_laurie
363 Followers 1K Following Postdoc at Oilthigh Dhùn Èideann. I do data wrangling for under-served languages.
Benjamin Lefaudeux �... @BenTheEgg
1K Followers 2K Following Back in the EU after some time in sunny California and happy Copenhagen. Mistral, prev Photoroom, Meta (xformers, FairScale), EyeTribe (acq)
Salman Masih @salmanpopa
317 Followers 3K Following Ph.D. in Computer Science: LLMs ❤️ | Looking for a place where excellence is tradition.
Guillaume Le Strat @GuillaumeLST
425 Followers 3K Following @zml_ai - hiring! Tech, startups & music Paris - South of France
processor @bwXRBhRpMI88095
58 Followers 7K Following
Simon Guo @simonguozirui
4K Followers 6K Following Beep Boop @thinkymachines | CS PhD student @Stanford | 🎓 @Berkeley_EECS
Chris Lattner @clattner_llvm
94K Followers 146 Following Building beautiful things like Mojo🔥 and MAX @Modular, lifting the world of production AI/ML software into a new phase of innovation. We’re hiring! 🚀🧠
Mark Saroufim @marksaroufim
16K Followers 1K Following Amdahl comes for us all mts & co-founder @coreautoai @pytorch @gpu_mode enjoyer
Marc G. Bellemare @marcgbellemare
17K Followers 348 Following Modelling @ Cohere. Ex RL research lead at Google Brain, DeepMind. Textbook author. Co-founder, Reliant AI.
Standard Kernel Co. @Standard_Kernel
2K Followers 4 Following Building AI Infrastructure with AI; fast kernels go brrr
Grad @Grad62304977
9K Followers 3K Following
Nathan Lambert @natolambert
92K Followers 921 Following Open model research @ something new. Prev. co-led Olmo at Ai2. Contact via email. Writes @interconnectsai Wrote The RLHF Book, 🏔️🏃♂️
Joelle Pineau @jpineau1
16K Followers 478 Following Chief AI Officer, @cohere Professor of Computer Science, @mcgillu Core academic member, @Mila_Quebec Ex-Meta (FAIR team)
Luke Drago @luke_drago_
4K Followers 832 Following beeping and booping @thinkymachines. previously @workshoplabs co-founder. opinions my own.
Workshop Labs @WorkshopLabs
3K Followers 1 Following Workshop Labs is an AI research company with a mission to make people irreplaceable.
Patrick C Toulme @PatrickToulme
11K Followers 327 Following TPU/XLA @google. Formerly worked on Meta MTIA and AWS Trainium. Opinions are my own. All blogs shared are personal work.
SemiAnalysis @SemiAnalysis_
132K Followers 27 Following
Ion Stoica @istoica05
9K Followers 20 Following Professor at UC Berkeley, co-founder of Databricks, Anyscale, LMArena, Conviva.
N8 Programs @N8Programs
10K Followers 238 Following Studying Applied Mathematics and Statistics at @JohnsHopkins. Studying In-Context Learning at The Intelligence Amplification Lab.
Ronan Collobert @trebolloc
2K Followers 26 Following OG Torch circa 2000. NLP from scratch. MLX. Aikido. Woodworker.
Modal @modal
32K Followers 160 Following AI infrastructure that developers love 💚 Run inference, sandboxes, batch processing, training, and many other things on Modal
Reiner Pope @reinerpope
19K Followers 459 Following CEO and founder, @MatXComputing, developing high throughput chips tailored for LLMs
Jarred Sumner @jarredsumner
180K Followers 644 Following building @bunjavascript at @anthropicai. formerly: @stripe (twice) @thielfellowship. high school dropout. npm i -g bun
U.S. Graphics Company @usgraphics
63K Followers 486 Following Engineering graphics. Check out our new typeface, Berkeley Mono → https://t.co/dUqr2XX9Wm
General Intuition @gen_intuition
12K Followers 21 Following The frontier lab for acting in space and time.
Gradium @GradiumAI
4K Followers 1 Following The voice layer for modern apps and agents. Real-time, scalable voice APIs: TTS, STT, turn-taking & voice cloning. Devs: build → https://t.co/r5CdNClhI5
stochasm @stochasticchasm
7K Followers 2K Following pretraining lead @arcee_ai • 25 • opinions my own
PolymathicAI @PolymathicAI
4K Followers 69 Following The Polymathic AI Collaboration. Shared account.
Perceptron AI @perceptroninc
3K Followers 0 Following The layer of intelligence that bridges the physical and digital worlds. https://t.co/Mmo3044h89
Pengyu Zhao @zpysky1125
3K Followers 286 Following LLM Lead @MiniMax_AI MiniMax Agent: https://t.co/WYkuer8tSV
Alexia Jolicoeur-Mart... @jm_alexia
25K Followers 2K Following Principal Researcher @ Microsoft 🐱💻 2025 ARC Prize Winner I build generative AI for images, videos, text, tabular data, weights, molecules, and video games.
Arnaud Stiegler @ArnaudStiegler
296 Followers 344 Following RL environments and reasoning at ReflectionAI
Sholto Douglas @_sholtodouglas
47K Followers 2K Following Scaling RL @AnthropicAI, ex @DeepMind - working towards intelligence too cheap to meter
LMSYS Org @lmsysorg
16K Followers 198 Following Large Model Systems Organization: We developed SGLang @sgl_project (https://t.co/OjwQadINKU), Chatbot Arena (now @arena), and Vicuna!
JingyuanLiu @JingyuanLiu123
4K Followers 573 Following https://t.co/D7zLeTZRMh is all you need | I am not Jianlin, just love his work... | Opinions are my own
Math, Inc. @mathematics_inc
13K Followers 0 Following Solve math, solve everything. Dedicated to superintelligence via autoformalization
Pierre Richemond 🇪... @TheOneKloud
3K Followers 1K Following Multimodal lead @cohere. @ImperialCollege PhD, Paris VI - @Polytechnique, ENST, @HECParis alum. Prev @GoogleDeepMind scientist, @GoldmanSachs trader. Views mine
Viraat Aryabumi @viraataryabumi
742 Followers 482 Following multimodal @cohere | ex-scholar @cohere_labs | ex-MLE @amazondevscot Opinions are my ownYou might like
