Wassim (Wes) Bouaziz @_Vassim

AI Security PhD student @MetaAI and @Polytechnique Previously @ENS_ULM @ENS_ParisSaclay I confront equations and inequalities💡 wesbz.github.io Paris' suburb Joined December 2010

Tweets

3K
Followers

721
Following

2K
Likes

3K

Piotr Bojanowski @p_bojanowski

3 weeks ago

I am happy to share the work of our team. The outcome of a collaborative effort, by a joyful group of skilled and determined scientists and engineers! Congrats to the team on this amazing milestone!

AI at Meta @AIatMeta

3 weeks ago

I am happy to share the work of our team. The outcome of a collaborative effort, by a joyful group of skilled and determined scientists and engineers! Congrats to the team on this amazing milestone!

289 757 4K 827K 2K

Download Video

5 21 220 18K 23

Federico Baldassarre @BaldassarreFe

3 weeks ago

Say hello to DINOv3 🦖🦖🦖 A major release that raises the bar of self-supervised vision foundation models. With stunning high-resolution dense features, it’s a game-changer for vision tasks! We scaled model size and training data, but here's what makes it special 👇

42 276 2K 217K 917

Download Image

Wassim (Wes) Bouaziz @_Vassim

4 weeks ago

Peer review ML conferences: > Only "top" X% get in > Jobs, grants, bonuses hinge on it > No penalty for bad-faith reviews > No cost for flooding submissions Who could have seen this going wrong? 🤭

Yi Ma @YiMaTweets

4 weeks ago

Peer review ML conferences: > Only "top" X% get in > Jobs, grants, bonuses hinge on it > No penalty for bad-faith reviews > No cost for flooding submissions Who could have seen this going wrong? 🤭

4 1 20 10K 2

0 0 5 360 0

Belen Alastruey @b_alastruey

a month ago

🚀New paper alert! 🚀 In our work @AIatMeta we dive into the struggles of mixing languages in largely multilingual Transformer encoders and use the analysis as a tool to better design multilingual models to obtain optimal performance. 📄: arxiv.org/abs/2508.02256 🧵(1/n)

1 16 73 6K 20

Download Image

João Maria Janeiro @JoaoMJaneiro

a month ago

If you are attending ACL2025 join our oral presentation! Happening at 15:00 in room 1.86 🙂

João Maria Janeiro @JoaoMJaneiro

11 months ago

If you are attending ACL2025 join our oral presentation! Happening at 15:00 in room 1.86 🙂

0 2 14 3K 3

0 3 6 644 0

Ambroise Odonnat @AmbroiseOdonnat

2 months ago

🚀 We are happy to organize the BERT²S workshop @NeurIPSConf 2025 on Recent Advances in Time Series Foundation Models. 🌐 berts-workshop.github.io 📜Submit by August 22 🎓Speakers and panelists: @ChenghaoLiu15 Mingsheng Long @zoe_piran @danielle_maddix @atalwalkar @qingsongedu

0 10 23 5K 3

Download Image

Ken Liu @kenziyuliu

2 months ago

heading to @icmlconf #ICML2025 next week! come say hi & i'd love to learn about your work :) i'll present this paper (arxiv.org/abs/2503.17514) on the pitfalls of training set inclusion in LLMs, Thursday 11am here are my talk slides to flip through: ai.stanford.edu/~kzliu/files/m…

Ken Liu @kenziyuliu

5 months ago

13 96 328 90K 200

Download Image

6 46 311 39K 181

Download Image

Pascale Fung @pascalefung

2 months ago

Our research on embodied AI agents that can perceive, learn, act and interact in the virtual and physical worlds. #metaAI #AIAgent #embodied #worldmodel #superintelligemce arxiv.org/abs/2506.22355

20 81 283 49K 199

Piotr Bojanowski @p_bojanowski

2 months ago

Why does Meta open-source its models? I talked about it with @kawecki_maciej looking at Dino, our computer vision model with applications in forest mapping, medical research, agriculture and more. Open-source boosts AI access, transparency, and safety. youtube.com/watch?v=eNGafi…

0 11 65 9K 9

Delip Rao e/σ @deliprao

2 months ago

Anthropic or Anthropic-sponsored safety papers

46 209 3K 144K 265

Download Image

Charles Arnal @arnal_charles

2 months ago

❓How to balance negative and positive rewards in off-policy RL❓ In Asymmetric REINFORCE for off-Policy RL, we show that giving less weight to negative rewards is enough to stabilize off-policy RL training for LLMs! 💪 (1/8) Paper: arxiv.org/abs/2506.20520

2 28 155 16K 127

Download Image

Ambroise Odonnat @AmbroiseOdonnat

2 months ago

Here is the recording with the slides for those interested! 🎤 youtu.be/UONvP1TL0-g?fe… 📊drive.google.com/file/d/14ZIopS… 📑arxiv.org/pdf/2410.02724 @Cohere_Labs @Cohere_Labs

Cohere Labs @Cohere_Labs

3 months ago

Here is the recording with the slides for those interested! 🎤 youtu.be/UONvP1TL0-g?fe… 📊drive.google.com/file/d/14ZIopS… 📑arxiv.org/pdf/2410.02724 @Cohere_Labs @Cohere_Labs

1 5 20 6K 0

Download Image

0 5 18 2K 0

Mathurin Videau @mathuvu_

3 months ago

We present an Autoregressive U-Net that incorporates tokenization inside the model, pooling raw bytes into words then word-groups. AU-Net focuses most of its compute on building latent vectors that correspond to larger units of meaning. Joint work with @byoubii 1/8