Negar Foroutan
@negarforoutan.bsky.social
#NLProc PhD Student at EPFL
Reposted by Negar Foroutan
🌍Introducing BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data!
LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data
We extend this effort to 45 new languages!
LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data
We extend this effort to 45 new languages!
October 15, 2025 at 10:53 AM
🌍Introducing BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data!
LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data
We extend this effort to 45 new languages!
LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data
We extend this effort to 45 new languages!
Reposted by Negar Foroutan
1/🚨 New preprint
How do #LLMs’ inner features change as they train? Using #crosscoders + a new causal metric, we map when features appear, strengthen, or fade across checkpoints—opening a new lens on training dynamics beyond loss curves & benchmarks.
#interpretability
How do #LLMs’ inner features change as they train? Using #crosscoders + a new causal metric, we map when features appear, strengthen, or fade across checkpoints—opening a new lens on training dynamics beyond loss curves & benchmarks.
#interpretability
September 25, 2025 at 2:02 PM
1/🚨 New preprint
How do #LLMs’ inner features change as they train? Using #crosscoders + a new causal metric, we map when features appear, strengthen, or fade across checkpoints—opening a new lens on training dynamics beyond loss curves & benchmarks.
#interpretability
How do #LLMs’ inner features change as they train? Using #crosscoders + a new causal metric, we map when features appear, strengthen, or fade across checkpoints—opening a new lens on training dynamics beyond loss curves & benchmarks.
#interpretability
🚨New Preprint!
In multilingual models, the same meaning can take far more tokens in some languages, penalizing users of underrepresented languages with worse performance and higher API costs. Our Parity-aware BPE algorithm is a step toward addressing this issue: 🧵
In multilingual models, the same meaning can take far more tokens in some languages, penalizing users of underrepresented languages with worse performance and higher API costs. Our Parity-aware BPE algorithm is a step toward addressing this issue: 🧵
August 11, 2025 at 12:28 PM
🚨New Preprint!
In multilingual models, the same meaning can take far more tokens in some languages, penalizing users of underrepresented languages with worse performance and higher API costs. Our Parity-aware BPE algorithm is a step toward addressing this issue: 🧵
In multilingual models, the same meaning can take far more tokens in some languages, penalizing users of underrepresented languages with worse performance and higher API costs. Our Parity-aware BPE algorithm is a step toward addressing this issue: 🧵
Stop by our poster presentation at @iclr-conf.bsky.social and discuss real multilingual evaluation!
Feel free to reach out anytime during the conference! We’d love to connect!
Feel free to reach out anytime during the conference! We’d love to connect!
If you’re at @iclr-conf.bsky.social this week, come check out our spotlight poster INCLUDE during the Thursday 3:00–5:30pm session!
I will be there to chat about all things multilingual & multicultural evaluation.
Feel free to reach out anytime during the conference. I’d love to connect!
I will be there to chat about all things multilingual & multicultural evaluation.
Feel free to reach out anytime during the conference. I’d love to connect!
🚀 Introducing INCLUDE 🌍: A multilingual LLM evaluation benchmark spanning 44 languages!
Contains *newly-collected* data, prioritizing *regional knowledge*.
Setting the stage for truly global AI evaluation.
Ready to see how your model measures up?
#AI #Multilingual #LLM #NLProc
Contains *newly-collected* data, prioritizing *regional knowledge*.
Setting the stage for truly global AI evaluation.
Ready to see how your model measures up?
#AI #Multilingual #LLM #NLProc
April 23, 2025 at 5:31 AM
Stop by our poster presentation at @iclr-conf.bsky.social and discuss real multilingual evaluation!
Feel free to reach out anytime during the conference! We’d love to connect!
Feel free to reach out anytime during the conference! We’d love to connect!
Reposted by Negar Foroutan
NEW PAPER ALERT: Generating visual narratives to illustrate textual stories remains an open challenge, due to the lack of knowledge to constrain faithful and self-consistent generations. Our #CVPR2025 paper proposes a new benchmark, VinaBench, to address this challenge.
April 1, 2025 at 9:09 AM
NEW PAPER ALERT: Generating visual narratives to illustrate textual stories remains an open challenge, due to the lack of knowledge to constrain faithful and self-consistent generations. Our #CVPR2025 paper proposes a new benchmark, VinaBench, to address this challenge.
Reposted by Negar Foroutan
Lots of great news out of the EPFL NLP lab these last few weeks. We'll be at @iclr-conf.bsky.social and @naaclmeeting.bsky.social in April / May to present some of our work in training dynamics, model representations, reasoning, and AI democratization. Come chat with us during the conference!
February 25, 2025 at 9:18 AM
Lots of great news out of the EPFL NLP lab these last few weeks. We'll be at @iclr-conf.bsky.social and @naaclmeeting.bsky.social in April / May to present some of our work in training dynamics, model representations, reasoning, and AI democratization. Come chat with us during the conference!
AI is reshaping #education, but are we ready? 🚨
Our new
@pnas.org
article explores how #LLMs challenge traditional assessments in higher education.
Instead of banning #AI, we argue for redesigning assessments to emphasize real-world problem-solving and ethical AI use.
Our new
@pnas.org
article explores how #LLMs challenge traditional assessments in higher education.
Instead of banning #AI, we argue for redesigning assessments to emphasize real-world problem-solving and ethical AI use.
December 5, 2024 at 10:20 AM
AI is reshaping #education, but are we ready? 🚨
Our new
@pnas.org
article explores how #LLMs challenge traditional assessments in higher education.
Instead of banning #AI, we argue for redesigning assessments to emphasize real-world problem-solving and ethical AI use.
Our new
@pnas.org
article explores how #LLMs challenge traditional assessments in higher education.
Instead of banning #AI, we argue for redesigning assessments to emphasize real-world problem-solving and ethical AI use.
Excited to share our work on INCLUDE! 🚀
INCLUDE sets a new standard for #LLM benchmarks—spanning 44 languages with a focus on regional knowledge and cultural context 🌍
Time for LLMs to meet the world where it is, not where it’s translated to!
#Multilingual #AI #NLProc
INCLUDE sets a new standard for #LLM benchmarks—spanning 44 languages with a focus on regional knowledge and cultural context 🌍
Time for LLMs to meet the world where it is, not where it’s translated to!
#Multilingual #AI #NLProc
🚀 Introducing INCLUDE 🌍: A multilingual LLM evaluation benchmark spanning 44 languages!
Contains *newly-collected* data, prioritizing *regional knowledge*.
Setting the stage for truly global AI evaluation.
Ready to see how your model measures up?
#AI #Multilingual #LLM #NLProc
Contains *newly-collected* data, prioritizing *regional knowledge*.
Setting the stage for truly global AI evaluation.
Ready to see how your model measures up?
#AI #Multilingual #LLM #NLProc
December 2, 2024 at 9:25 PM
Excited to share our work on INCLUDE! 🚀
INCLUDE sets a new standard for #LLM benchmarks—spanning 44 languages with a focus on regional knowledge and cultural context 🌍
Time for LLMs to meet the world where it is, not where it’s translated to!
#Multilingual #AI #NLProc
INCLUDE sets a new standard for #LLM benchmarks—spanning 44 languages with a focus on regional knowledge and cultural context 🌍
Time for LLMs to meet the world where it is, not where it’s translated to!
#Multilingual #AI #NLProc
Reposted by Negar Foroutan
[email protected] is hiring for multiple positions in CS (including one open call): www.epfl.ch/about/workin...
Apply to come join us in Beautiful Lausanne!
Apply to come join us in Beautiful Lausanne!
Open Faculty Positions
-
www.epfl.ch
November 26, 2024 at 11:40 AM
[email protected] is hiring for multiple positions in CS (including one open call): www.epfl.ch/about/workin...
Apply to come join us in Beautiful Lausanne!
Apply to come join us in Beautiful Lausanne!
Reposted by Negar Foroutan
EPFL's new AI Center has a Call for applications for postdoc fellowships in all AI-related areas. Come join if you're interested in working with me and fantastic AI colleagues!
Extra Perk: We actually do have lots of GPUs !
Deadline: November 29th
More info at:
www.epfl.ch/research/fun...
Extra Perk: We actually do have lots of GPUs !
Deadline: November 29th
More info at:
www.epfl.ch/research/fun...
EPFL AI Center Postdoctoral Fellowships
The EPFL AI Center Postdoctoral Fellowship call for proposals is now open with a deadline on 29 November 2024 (17:00 CET).Applications are encouraged from researchers at the postdoctoral level with a ...
www.epfl.ch
November 26, 2024 at 11:45 PM
EPFL's new AI Center has a Call for applications for postdoc fellowships in all AI-related areas. Come join if you're interested in working with me and fantastic AI colleagues!
Extra Perk: We actually do have lots of GPUs !
Deadline: November 29th
More info at:
www.epfl.ch/research/fun...
Extra Perk: We actually do have lots of GPUs !
Deadline: November 29th
More info at:
www.epfl.ch/research/fun...