banner
cohereforai.bsky.social
Cohere Labs
@cohereforai.bsky.social
460 followers 12 following 170 posts
@Cohere.com's non-profit research lab and open science initiative that seeks to solve complex machine learning problems. Join us in exploring the unknown, together. https://cohere.com/research
cohere.com
Posts Media Videos Starter Packs
Pinned
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · Jan 15
We are committed to making meaningful progress in machine learning research through open collaboration. Follow this 🧵to stay on top of our research contributions.
58 2 18
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 23h
Read the paper here: https://arxiv.org/abs/2504.11829
1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 23h
Today at COLM, we are excited to share our work Déjà Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation, during Poster Session 4, 4:30 - 6:30pm.

Come connect with paper authors @juliakreutzer.bsky.social and @kocmitom.bsky.social.
1 3
Reposted by Cohere Labs
juliakreutzer.bsky.social
Julia Kreutzer @juliakreutzer.bsky.social · 6d
💡A collaborative➕diverse team is key. In real life as in the LLM world 💪🦾
Check out our latest work that builds on this insight. 👇
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 7d
Is Best-of-N really the best use of your inference compute?

Introducing Fusion-of-N: a simple and powerful way to advance inference and distillation beyond Best-of-N.
1 1 3
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 7d
📜Paper link: https://arxiv.org/abs/2510.00931

Led by: Ammar Khairi, @juliakreutzer.bsky.social, Daniel D'souza @mziizm.bsky.social
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 7d
We are excited to present FusioN as a plug-and-play replacement to Best-of-N, shifting from a monolithic selection framework to collaborative synthesis one that embraces the diverse strengths of today’s leading open LLMs.
1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 7d
How does FusioN use the same sample pool more effectively than BoN?

🧩While BoN picks just one sample per problem, FusioN synthesises one output from all samples – treating them as collaborators whose strengths can be integrated, not competitors in a zero-sum game.
1 1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 7d
Want the wisdom-of-the-crowd in 1 model?

🧑‍🎓🧑🏽‍🎓👨🏾‍🎓Fusion-of-N distills multiple teachers into richer synthetic data than BoN, training students that achieve bigger downstream gains, even surpassing teachers on multilingual factual reasoning 🌎
1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 7d
Test-time scaling doesn't need to waste samples, Fusion-of-N turns every sample into signal; outperforming BoN across tasks, languages and models. 🚀

Fusion-of-N boosts CommandA win-rates vs Gemini-2.5 Pro +8.3% across 11 languages – a +4.0% improvement over BoN 🥇
1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 7d
Fusion-of-N uses an LLM (the fusor) to merge multiple candidate answers into one 💎

Instead of selecting only one response, Fusion-of-N creates an even better answer by integrating insights across all samples 🏅
1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 7d
Is Best-of-N really the best use of your inference compute?

Introducing Fusion-of-N: a simple and powerful way to advance inference and distillation beyond Best-of-N.
1 1 2
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 9d
Apply now: https://jobs.ashbyhq.com/cohere/7ec9eaf4-8cfc-4977-9041-86f73e7ab10b
1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 9d
We’re not your average lab. We’re a hybrid research environment dedicated to revolutionizing the ML space.

And we’re hiring a Senior Research Scientist to co-create with us.

If you believe in research as a shared, global effort — this is your chance.
1 3 4
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 10d
Led by: Srishti Gureja, Elena Tommasone, Jingyi He, @sarahooker.bsky.social, Matthias Galle, and @mziizm.bsky.social

📄 Paper: https://arxiv.org/abs/2509.20837
1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 10d
🔹 The future of synthetic training hinges on rethinking verification. It’s calibrated verification: complex, diverse test suites combined with flexible signals that break the Verification Ceiling and improve code LLMs.
1 1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 10d
🔹 We also find that LLMs can serve as soft verifiers. Their judgments recover useful data and often match or surpass formal unit tests selection.
1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 10d
🔹 Relaxing verification thresholds boosts performance but only with sufficiently complex test suites. Correctness still matters, but how we define it is the real issue.
1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 10d
We find:

🔹 Rigid verification risks biasing toward easy problems, while richer correctness signals preserve both quality and diversity.
1
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 10d
What if the way we verify synthetic code is limiting model performance?

In our latest work we uncover the Verification Ceiling Problem: strict “all tests must pass” rules throw away useful data, while weak tests let errors through.
1 2
Reposted by Cohere Labs
mziizm.bsky.social
Marzieh Fadaee @mziizm.bsky.social · Sep 5
I'm excited to share that I'll be stepping into the role of Head of @cohereforai.bsky.social. It's an honor and a responsibility to lead such an extraordinary group of researchers pushing the boundaries of AI research.
1 2 11
Reposted by Cohere Labs
cjpberry.bsky.social
Christopher Berry @cjpberry.bsky.social · 25d
Papers In The Park 14. Last one of the season! Still great weather. Surprising. Anthony is presenting the “Why Language Models Hallucinate”.

Thanks to @cohereforai.bsky.social for the copies and pizza.
1 2
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · 14d
🚨 Rare opportunity: Cohere Labs is hiring a Research Scientist!

If you’re passionate about studying fundamental AI problems and working in a globally collaborative, open-science environment, this is for you.

Apply here: jobs.ashbyhq.com/cohere/7ec9e...
5
Reposted by Cohere Labs
cjpberry.bsky.social
Christopher Berry @cjpberry.bsky.social · Jul 26
It’s papers in the park 7! Thanks to @cohereforai.bsky.social for the papers and the pizza, and to Alvin and Anthony for organizing.

It’s easily one of funnest paper reads in the city!
1 3
Reposted by Cohere Labs
mziizm.bsky.social
Marzieh Fadaee @mziizm.bsky.social · Aug 13
Breaking into AI research is harder than ever, and early-career researchers face fewer chances to get started.

Entry points matter.

We started the Scholars Program 3 years ago to give new researchers a real shot — excited to open applications for year 4✨
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · Aug 13
Applications are now open for the next cohort of the Cohere Labs Scholars Program! 🌟

This is your chance to collaborate with some of the brightest minds in AI & chart new courses in ML research. Let's change the spaces breakthroughs happen.

Apply by Aug 29.
1 3 6
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · Aug 15
Check out the full blogpost here: https://cohere.com/blog/elo-ratings-beyond-arena-style-evaluations

Great to collaborate with Adithya Venkatadri Hulagadri, @mziizm.bsky.social‬, @jiangangngui.bsky.social‬, and @juliakreutzer.bsky.social‬ on this exploration.
2
cohereforai.bsky.social
Cohere Labs @cohereforai.bsky.social · Aug 15
In this blogpost we propose a 3rd path:
✅ Balanced sampling across languages/tasks
✅ Offline pseudo-pairwise comparisons (Bradley-Terry)
✅ Confidence intervals & transparent breakdowns

The result? Rankings that better reflect real model utility.
1 2