🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Very proud to introduce Kaleidoscope ✨🌿 🌍 18 languages (Bengali → Spanish) 📚 14 subjects (Humanities → STEM) 📸 55% requiring image understanding! A very important open science collaboration — which extends in-language evaluation for vision models to many more languages.

A year ago we released LBBP - a drop-in replacement of HumanEval that was more challenging and less leaked Internally we have been using the multilingual version of this for benchmarking, and as code is not only python we decided to release that as well huggingface.co/datasets/Coher…

How exactly was the initial Chatbot Arena version of Llama 4 Maverick different from the public HuggingFace version?🕵️ I used our Feedback Forensics app to quantitatively analyse how exactly these two models differ. An overview…👇🧵

Really enjoyed giving this talk. Thanks for hosting and for the great questions! Tom Hosking you might recognise this slide 😅

Attending #ICLR2025 and interested in #LLM, #Alignment, or #SelfImprovement? Then come by and check out our work from cohere: "Self-Improving Robust Preference Optimization" - a new alignment method that unlocks self-refinement in LLMs! 📍 Poster Session 4 — Friday, 3–5:30 PM

If you want to learn more about how LLMs pick up reasoning abilities from procedural knowledge in pretraining, visit poster #208 in Hall 3 at 3pm today ICLR 2026 #ICLR #ICLR25 #ICLR2025

At #ICLR2025? Come and see Laura Ruis present these amazing results on how LLMs exploit data in different ways to learn facts vs capabilities. Happening now at poster 208 in Hall 3! 🚀

Recently overheard ICLR 2026: influence functions for LLMs are useless. Poster #208 disagrees 🤔

Congrats to our Cohere colleagues for their paper “Improving Reward Models with Synthetic Critiques” being presented at NAACL this week! 🎉 Read the paper: arxiv.org/pdf/2405.20850  Work led by Daniella Ye, Fraser, Max Bartolo, Phil Blunsom, Jon Ander Campos and Matthias Gallé

Join us to mark the end of Expedition Aya, our six-week global open-build challenge designed to accelerate ML research progress in multilingual, multimodal and efficiency✨ Top teams will present their key findings and innovations and our judges will select 5 winning projects🏆

Massive congrats team Afri-Aya, really great work! 🤩

the command-a paper is one of my top 5 papers of the year for sure cohere.com/research/paper…

Kudos to cohere for releasing 6 proper research papers in May alone, while publications of other western labs increasingly read like advertisements! I recently read the Command A technical report and it contains much more detail than other model reports. Looking at recent

Looking forward to sharing some of our recent research contributions at Machine Learning Street Talk's first London AI meetup 🤩

We’re looking for a Research Engineer / Scientist with a focus on Data Analysis and Evaluation to join the post-training team at Cohere! More details and application here: jobs.ashbyhq.com/cohere/6170371… Feel free to reach out if you'd like to know more!

LLMs can be programmed by backprop 🔎 In our new preprint, we show they can act as fuzzy program interpreters and databases. After being ‘programmed’ with next-token prediction, they can retrieve, evaluate, and even *compose* programs at test time, without seeing I/O examples.

Really enjoyed discussing the state of AI benchmarking alongside Prof Mark Bishop, Timothy Nguyen, Enzo Blindow & Tim Scarfe at Machine Learning Street Talk's first in-person event in London yesterday. Looking forward to many more!

🎤 Meet our expert panelists! Join Albert Gu, Alisa Liu, Kris Cao, Sander Land, and Yuval Pinter as they discuss the Future of Tokenization on July 18 at 3:30 PM at TokShop at #ICML2025.