Kelly Marchisio @NeurIPS

Multilingualilty Lead @cohere. Formerly: PhD @jhuclsp, Alexa Fellow @amazon, dev @Google, MPhil @cambridgenlp, EdM @hgse 🔑🔑¬🧀 (@kelvenmar20)

[Kelly Marchisio @NeurIPS @cheeesio]

sidenote, this comic is 19 years old. How... how did that happen.

[Kelly Marchisio @NeurIPS @cheeesio]

Omg. First day *really* agentic coding. This me rn 🤺⚔️
https://t.co/W50byjkN4t

[Slator @slatornews]

👉 https://t.co/6CY6PLvLI7
While reasoning-enabled #LLMs are among the strongest 🔝 performers in #AI #translation benchmarks, a new study suggests that prompting them to explain their reasoning before translating can hurt translation quality.
@rajaee_sara @mziizm @cheeesio @Cohere_Labs @UvA_Amsterdam @cohere #xl8 #t9n

[Kelly Marchisio @NeurIPS @cheeesio]

“What language is this text written in?” - a question so easy to pose, yet surprisingly difficult to answer!

[EleutherAI @AiEleuther]

Announcing our latest paper: CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data

In collaboration with @CommonCrawl @MLCommons and @JohnsHopkins we worked with 80+ native speaker annotators to build a LID benchmark on actual Common Crawl text covering 109 languages. Existing evaluations overestimate how well LangID works on web data.

[Kelly Marchisio @NeurIPS @cheeesio]

@BlancheMinerva Wow this is awesome, and so needed!! A great contribution to the community!

[Piotr Nawrot @p_nawrot]

🌟🚀Sparse Attention Models Can Get Sparser

We've updated The Sparse Frontier—the largest empirical analysis of training-free sparse attention to date—from Qwen 2.5 to 3 model families, now including Llama 3.1 and Gemma 3.

Key findings:

📊 Larger sparse models outperform smaller dense ones at equal compute cost. Only high-sparsity configs lie on the Pareto frontier for long sequences.

🔬 Already sparse? You can go sparser. Gemma 3 has 5/6 layers as Sliding Window Attention by design—yet additional sparsification of the remaining dense layers still yields efficiency gains at scale.

📈 Longer sequences tolerate higher sparsity. From 9 models × 6 methods × 9 tasks: fixed-budget methods in production are suboptimal. Token budget should grow sublinearly with context length.

Co-authors: Robert Li, Renjie Huang, @seb_ruder, @cheeesio, @PontiEdoardo.
Special shout-out to @faridlazuarda who updated our repo to vLLM v1 and made Gemma3 evaluations possible.

Links in the comments ⬇️

[Kelly Marchisio @NeurIPS @cheeesio]

Our Multilingual Team at @cohere is hiring interns!

If you are a current PhD student working in multilinguality and would like to work with our team, please apply below, reach out! 🌍🌏🌎

(The below says “Winter”, but we hire year-round)

https://t.co/Uwhh7aE5LE

[Kelly Marchisio @NeurIPS @cheeesio]

Three emails in the past ~week addressed to “Emma”. This can’t be a coincidence — hive-mind, what is this?

[MT Group at FBK @fbk_mt]

Our pick of the week by @dhairya_su47605: "How Does #Quantization Affect #Multilingual #LLMs?" by @cheeesio, @TheyCallMeMr_, Hongyu Chen, @d_aumiller, @ahmetustun89, @sarahookr, @seb_ruder (Findings EMNLP, 2024)

[Dhairya Suman @dhairya_su47605]

Pick of the week @fbk_mt: How Does Quantization Affect Multilingual LLMs?

Quantization has become a widely adopted technique for model compression. This work investigates the impact of quantization on different languages in multilingual LLMs.

https://t.co/A82iW9Myek

[Kelly Marchisio @NeurIPS @cheeesio]

Announcing - Moms Who ML! 🐣🍼

I landed in San Diego to a video call from my 15-month-old -- she licked the camera then put me in this bag of Mega Bloks👅

If you can relate, let's support one another!

Search for the group on the #NeurIPS2025 app, and we'll expand after!

[Kelly Marchisio @NeurIPS @cheeesio]

Looking forward to #neurips2025 next week! Come say hi at the @cohere booth!

[David Ifeoluwa Adelani 🇳🇬 @davlanade]

First invited talk by Kelly Marchisio @cheeesio

[Dwarak @DwaraknathG]

I am hiring highly skilled performance engineers for my team! You will be working on optimising pretraining for models >100B params on O(1000s) of GPUs, and hardware-aligned architecture design. We are cooking a lot of very exciting projects and I can safely say you will have a lot of fun! Link in thread. <3

[Kelly Marchisio @NeurIPS @cheeesio]

Big thanks to @slatornews for hosting me at #SlatorCon Silicon Valley last month. I loved giving attendees an inside look into how SOTA multilingual LLMs are built 🤖🌍

[Slator @slatornews]

Kelly Marchisio, Multilingual Team Lead at @cohere, shared an inside look at building 🧑‍💻 a #multilingual #LLM and advancing #AI #translation at #SlatorCon Silicon Valley 2025.
#Cohere #LLMs #xl8 #t9n @cheeesio
https://t.co/AonaWd7MQ0

[Kelly Marchisio @NeurIPS @cheeesio]

I had a great time speaking at #SlatorConSV25 today!

[Slator @slatornews]

The future of multilingual AI 🚀 is here. At #SlatorConSV25, @cohere's @cheeesio explains how to build massively multilingual LLMs, from technical foundations to the current landscape and what comes next.
#MultilingualAI #LLMs #CommandA

[Kelly Marchisio @NeurIPS @cheeesio]

@taneemishere Cohere does hire in multimodality: https://t.co/DVNg39GzE1

[Kelly Marchisio @NeurIPS @cheeesio]

From the Multilingual Team kitchen straight to you 🧑‍🍳 Enjoy Command A Translate! (we're hiring!)

[Cohere @cohere]

Introducing Command A Translate, our state-of-the-art model designed for high-quality translation tasks.

[Matthias Gallé @mgalle]

Where machine translation goes, AI goes. This has been true since 1954 (MT made front-page of NYT, 2 years before the Dartmouth workshop)

We just released the best translation model ever