UndefBehavior's profile picture.

Caio

@UndefBehavior

Caio reposted

Rennes 2 la Rouge, on se retrouve ce soir à 18h pour discuter de la situation politique explosive. Aller à Rennes 2 un jour de chute du gouvernement… la révolution est proche 😂✊🏼🇵🇸

AnasseKazib's tweet image. Rennes 2 la Rouge, on se retrouve ce soir à 18h pour discuter de la situation politique explosive.

Aller à Rennes 2 un jour de chute du gouvernement… la révolution est proche 😂✊🏼🇵🇸

Caio reposted

5) EuroBERT: Scaling Multilingual Encoders for European Languages w/ @N1colAIs @gisship @DuarteMRAlves @AyoubHammal @UndefBehavior @Fannyjrd_ @ManuelFaysse @peyrardMax @psanfernandes @RicardoRei7 @PierreColombo6 @tomaarsen - Poster session 5, Thu Oct 9, 11:00 AM – 1:00 PM


Caio reposted

As you react to EMNLP rebuttals, Please make sure to substantiate your stance on why the score you have chosen is justified Keeping the information latent doesn't help authors understand your point to improve their work, and doesn't help AC/SAC make a grounded and fair decision.

abeirami's tweet image. As you react to EMNLP rebuttals, Please make sure to substantiate your stance on why the score you have chosen is justified

Keeping the information latent doesn't help authors understand your point to improve their work, and doesn't help AC/SAC make a grounded and fair decision.

Caio reposted

Simple example for how errors can creep into our papers through LLM use: I had a statistic for 2020. I googled the same statistic for 2023. AI overview tells me the statistic for 2023 & provides a link to support the claim. The link is to a 2023 article citing the 2020 statistic.


Caio reposted

Having trouble choosing a track for your ARR / EMNLP submissions? Take a look at this blog post for more information: 2025.emnlp.org/track-changes/


Caio reposted

If you submitted to ICML and TMLR as an author, where did you get higher review quality (grounded, fair, and helped improve your paper)? 𝐏𝐥𝐞𝐚𝐬𝐞 𝐝𝐞𝐜𝐨𝐮𝐩𝐥𝐞 𝐭𝐡𝐞 𝐮𝐥𝐭𝐢𝐦𝐚𝐭𝐞 𝐟𝐚𝐢𝐭𝐡 𝐨𝐟 𝐩𝐚𝐩𝐞𝐫 𝐟𝐫𝐨𝐦 𝐲𝐨𝐮𝐫 𝐣𝐮𝐝𝐠𝐞𝐦𝐞𝐧𝐭 𝐨𝐟 𝐪𝐮𝐚𝐥𝐢𝐭𝐲.


Caio reposted

Current KL estimation practices in RLHF can generate high variance and even negative values! We propose a provably better estimator that only takes a few lines of code to implement.🧵👇 w/ @xtimv and Ryan Cotterell code: arxiv.org/pdf/2504.10637 paper: github.com/rycolab/kl-rb

afra_amini's tweet image. Current KL estimation practices in RLHF can generate high variance and even negative values! We propose a provably better estimator that only takes a few lines of code to implement.🧵👇
w/ @xtimv and Ryan Cotterell
code: arxiv.org/pdf/2504.10637
paper: github.com/rycolab/kl-rb

Caio reposted

ARR May (EMNLP) cycle opens May 5th. Reminder: (1) All resubmissions from past cycles MUST be declared, or they will be desk-rejected (automated checks against past cycles apply); (2) The responsible checklist must be carefully completed, or the paper gets a desk reject.


Caio reposted

Today I had my paper rejected by ICML. I don’t like to complain about the free voluntary work that the AC and reviewers do, but this was one of the most careless reviews and AC we ve had. Our rejection was based on this:


Caio reposted

On a un souci avec la sociologie des étudiants en médecine. Pour pouvoir se balader avec une pancarte pareille sans que tes camarades te disent « mec t’es au courant que Mulhouse c’est une super grande ville ? » (et pas vraiment un désert médical en plus) faut un sacré entre soi

NicolasFramont's tweet image. On a un souci avec la sociologie des étudiants en médecine. Pour pouvoir se balader avec une pancarte pareille sans que tes camarades te disent « mec t’es au courant que Mulhouse c’est une super grande ville ? » (et pas vraiment un désert médical en plus) faut un sacré entre soi

Caio reposted

ModernBERT or DeBERTaV3? What's driving performance: architecture or data? To find out we pretrained ModernBERT on the same dataset as CamemBERTaV2 (a DeBERTaV3 model) to isolate architecture effects. Here are our findings:


Caio reposted

Bah la team pk vous masquez mon commentaire ? ils sont public nos résultats pourtant ^^ (À gauche sur mon compte et à droite sur celui d'un pote)

mathurien_'s tweet image. Bah la team pk vous masquez mon commentaire ? ils sont public nos résultats pourtant ^^
(À gauche sur mon compte et à droite sur celui d'un pote)
mathurien_'s tweet image. Bah la team pk vous masquez mon commentaire ? ils sont public nos résultats pourtant ^^
(À gauche sur mon compte et à droite sur celui d'un pote)

Caio reposted

📢 #ACL2025NLP Dear community! The reviewing deadline for ACL 2025 is approaching -- 23 March! We received over 8000 submissions, the highest number in ACL history. It is particularly important that you submit your reviews on time. A big thank you in advance for all your efforts!


Caio reposted

If you are a recent graduate, please! check this out: missing.csail.mit.edu "The Missing Semester of Your CS Education"

missing.csail.mit.edu

The Missing Semester of Your CS Education

The Missing Semester of Your CS Education

holy shit

jxnlco's tweet image. holy shit


Caio reposted

>Transformer without normalization >Looks inside >Normalization to the l^∞ unit ball x.com/liuzhuang1234/…

mgostIH's tweet image. >Transformer without normalization
>Looks inside
>Normalization to the l^∞ unit ball
x.com/liuzhuang1234/…

New paper - Transformers, but without normalization layers (1/n)

liuzhuang1234's tweet image. New paper - 

Transformers, but without normalization layers (1/n)


Caio reposted

Our upcoming #AISTATS2025 paper is out: “Sparse Activations as Conformal Predictors” with Margarida Campos, João Calém, Sophia Sklaviadis, and @mariotelfig: arxiv.org/abs/2502.14773. This paper puts together two lines of research, dynamic sparsity and conformal prediction. 🧵

andre_t_martins's tweet image. Our upcoming #AISTATS2025 paper is out: “Sparse Activations as Conformal Predictors” with Margarida Campos, João Calém, Sophia Sklaviadis, and @mariotelfig:

arxiv.org/abs/2502.14773. 

This paper puts together two lines of research, dynamic sparsity and conformal prediction. 🧵

Caio reposted

🇪🇺 One month after the AI Action Summit 2025 in Paris, I am thrilled to announce EuroBERT, a family of multilingual encoder exhibiting the strongest multilingual performance for task such as retrieval, classification and regression over 15 languages, mathematics and code. ⬇️ 1/6

N1colAIs's tweet image. 🇪🇺 One month after the AI Action Summit 2025 in Paris, I am thrilled to announce EuroBERT, a family of multilingual encoder exhibiting the strongest multilingual performance for task such as retrieval, classification and regression over 15 languages, mathematics and code. ⬇️ 1/6

Loading...

Something went wrong.


Something went wrong.