Kelly Marchisio (St. Denis)
@cheeesio
Followers
2K
Following
3K
Media
48
Statuses
686
Multilingualilty Lead @cohere. Formerly: PhD @jhuclsp, Alexa Fellow @amazon, dev @Google, MPhil @cambridgenlp, EdM @hgse 🔑🔑¬🧀 (@kelvenmar20)
Connecticut, USA
Joined June 2019
RT @Cohere_Labs: @weiyinko_ml was one of the earliest members of our Open Science Community and an early collaborator on our open science r….
0
2
0
“where is the most extensible place to add this fnct call?” 🤖 Memory jogged: “oh, of course that's the best spot.” . I needed code familiarity and years of non-GenAI-influenced experience to reap the time-savings w/o error; but as a time-strapped manager, this was a godsend! 2/2.
0
0
4
Wow. Coding with GenAI continues to impress, but highlights the need for strong knowledge of the code *without* help. I opened up a once-familiar codebase, but one I haven’t looked at seriously in a year. Instead of hours spent re-familiarizing, I asked an LLM, (1/2).
1
0
7
RT @davlanade: Excited to announce the call for papers for the Multilingual Representation Learning workshop #EMNLP2025 .
0
11
0
RT @weiyinko_ml: We're looking for a new member for the multilingual team with a focus on data engineering! Please apply at the link below:.
0
7
0
Code-release from our superstar intern, @p_nawrot!.• Write sparse attn patterns in 50 lines, not 5k .• Compatibility w models supported by vLLM, support for TP.• 6 SOTA baselines with optimized implementations + 9 eval tasks .• Research-grade extensibility = rapid prototyping.
We built sparse-frontier — a clean abstraction that lets you focus on your custom sparse attention implementation while automatically inheriting vLLM’s optimizations and model support. As a PhD student, I've learned that sometimes the bottleneck in research isn't ideas — it's
1
1
17
RT @PontiEdoardo: 🚀 By *learning* to compress the KV cache in Transformer LLMs, we can generate more tokens for the same compute budget.….
0
27
0
RT @Cohere_Labs: Here are key recommendations to make AI safer & more equitable for everyone:. 🌐 Incentivize the creation of open-access mu….
0
1
0
RT @Cohere_Labs: Over 7000 languages are spoken worldwide 🌐, but AI safety efforts focus on only a fraction of them. Our latest paper dra….
0
22
0
RT @p_nawrot: Tomorrow at 6pm CET I'm giving a talk about our latest work on Sparse Attention, at @Cohere_Labs. I plan to describe the fie….
0
3
0
RT @Cohere_Labs: Our ML Efficiency group is looking forward to welcoming @p_nawrot next week on May 28th, for a session on "The Sparse Fron….
0
4
0
Welcome, Ruochen! ✨.
🌟 Little late but I just started my internship @cohere, cooking more multilingual things with the amazing @cheeesio and @SCahyawijaya. Will be in nyc for June and July, hmu!🗽.
1
0
9
I’m excited to see what you’ve built! 🚀.
0
0
8
Result of @robinson_n8’s internship on the Cohere multilingual team last year! Check it out!.
Many LLMs struggle to produce Dialectal Arabic. As practitioners attempt to mitigate this, new evaluation methods are needed. We present AL-QASIDA (Analyzing LLM Quality + Accuracy Systematically In Dialectal Arabic), a comprehensive eval of LLM Dialectal Arabic proficiency (1/7)
0
0
11
0
1
13
RT @seb_ruder: The Sparse Frontier. Efficient sparse attention methods are key to scale LLMs to long contexts. We conduct the largest-scale….
0
29
0
