Caio @UndefBehavior

Paris, France Joined August 2017

Tweets

2K
Followers

532
Following

1K
Likes

8K

Ahmad Beirami @abeirami

3 months ago

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.

3 7 66 10K 3

Download Image

Vered Shwartz @VeredShwartz

4 months ago

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.

3 5 29 3K 4

EMNLP 2025 @emnlpmeeting

5 months ago

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/

1 4 25 4K 8

Quiveron @quiveron_x

5 months ago

youtu.be/cyyR7j2ChCI?si…

6 37 337 111K 288

Ahmad Beirami @abeirami

5 months ago

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.

9 9 43 18K 16

Afra Amini @afra_amini

5 months ago

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

4 34 128 14K 84

Download Image

ACLRollingReview @ReviewAcl

5 months ago

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.

0 6 38 6K 3

Robert M. Gower 🇺🇦 @gowerrobert

5 months ago

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:

9 15 413 79K 113

Nicolas Framont @NicolasFramont

5 months ago

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

154 893 6K 284K 172

Download Image

Wissam Antoun @wissam_antoun

6 months ago

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:

4 17 80 7K 52

🚩mathurin 🇳🇨🇵🇸 @mathurien_

6 months ago

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)

4 6 45 2K 2

Download Image

ACL 2025 @aclmeeting

6 months ago

📢 #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!

1 17 53 10K 3

Pasquale Minervini @PMinervini

7 months ago

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

jason liu @jxnlco

7 months ago

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

482 281 6K 1.3M 1K

Download Image

0 2 12 1K 6

mgostIH @mgostIH

7 months ago

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

Zhuang Liu @liuzhuang1234

7 months ago

>Transformer without normalization >Looks inside >Normalization to the l^∞ unit ball x.com/liuzhuang1234/… https://t.co/1wUgrAol6h

76 598 4K 1.3M 2K

Download Image

9 19 596 73K 156

Download Image

Andre Martins @andre_t_martins

7 months ago

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. 🧵

1 4 21 3K 5

Download Image

Nicolas Boizard @N1colAIs

7 months ago

🇪🇺 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

15 47 188 49K 63

Download Image

Sasha Rush @srush_nlp

7 months ago

Linear Attention and Beyond: Interactive Tutorial with Songlin Yang (@SonglinYang4 MIT/Flash Linear Attention) I didn’t follow some of the recent results, so I zoomed Songlin and she explained it all to me for two hours 😂 youtu.be/d0HJvGSWw8A