Sanae Lotfi (@LotfiSanae) / X

Sanae Lotfi

424 posts

Sanae Lotfi

@LotfiSanae

AI Research Scientist @MetaAI (FAIR) | PhD from @nyuniversity

Menlo Park, CA

Joined August 2020

Sanae Lotfi
@LotfiSanae
Jul 21, 2022
This Moroccan Arab Muslim first-generation woman just gave her first long talk for her award-winning paper at #ICML2022! I dedicate this achievement to all the underrepresented groups that I proudly represent! So overwhelmed by all the support that I received! Many thanks! 1/2
Sanae Lotfi
@LotfiSanae
Aug 11, 2025
Excited to share two milestones: I have officially completed my PhD at NYU, and I have joined Meta AI’s Fundamental AI Research (FAIR) team in the Bay Area as a Research Scientist! I’m so grateful to many people who made this possible; more in this thread 🧵
69K
Sanae Lotfi
@LotfiSanae
Oct 14, 2022
I'm so grateful and honored to receive the Microsoft Research PhD Fellowship @MSFTResearch!!🥳 This fellowship means that my research and that of my group led by @andrewgwils is recognized as meaningful and impactful for the machine learning community! 1/3
Sanae Lotfi
@LotfiSanae
Jul 20, 2022
I'm so proud that our paper on the marginal likelihood won the Outstanding Paper Award at #ICML2022!!! Congratulations to my amazing co-authors @Pavel_Izmailov, @g_benton_, @micahgoldblum, @andrewgwils 🎉 Talk on Thursday, 2:10 pm, room 310 Poster 828 on Thursday, 6-8 pm, hall E
Andrew Gordon Wilson
@andrewgwils
May 19, 2022
I'm happy that this paper will appear as a long oral at #ICML2022! It's the culmination of more than a decade of thinking about when the marginal likelihood does and doesn't make sense for model selection and hyper learning, and why. It was also a great collaborative effort.
Sanae Lotfi
@LotfiSanae
Mar 31, 2023
We talk a lot about LLMs but you know what we don’t talk enough about? PhD student mental health, community building, and effective research practices! That’s why Yaniv Yacoby and I are organizing a workshop at NYU entitle “Everything I wish I knew as I navigated my PhD”. 1/3 👇
65K
Sanae Lotfi
@LotfiSanae
Jul 25, 2022
I appreciate this apology, but I am saddened that you are still implying a lack of scientific integrity. 1/N
Andreas Kirsch 🇺🇦
@BlackHC
Jul 25, 2022
I'm sorry for the negative attention I brought on @LotfiSanae in what should have been a joyous moment and who has authored an amazing & exciting paper on a complex topic. My intention was scientific integrity, but I lost sight of the broader context of this academic debate &
Sanae Lotfi
@LotfiSanae
Dec 5, 2023
It was a great honor to be distinguished as a Rising Star in ML by @ml_umd 🥳 Many thanks to the organizers and professors with whom I had great discussions! Next stop: #NeurIPS2023; so excited to share our work on generalization bounds for LLMs and host @MuslimsinML there!
16K
Sanae Lotfi
@LotfiSanae
Mar 31, 2023
Went to Harvard to give a talk about our work on the marginal likelihood and PAC-Bayes bounds, ended up meeting @ConanOBrien there. It turns out he’s a big Bayesian!
16K
Sanae Lotfi
@LotfiSanae
Dec 16, 2023
Can LLMs generalize meaningfully beyond their training data? We answer this question by computing the first non-vacuous generalization bounds for LLMs. Wanna learn more? Find us the M3L and SSL workshops 😉 w/ @m_finzi @KuangYilun @timrudner @micahgoldblum @andrewgwils
15K
Sanae Lotfi
@LotfiSanae
Feb 29, 2024
Are LLMs able to meaningfully generalize beyond their training data? We address this question by computing the first non-vacuous generalization bounds for LLM pretraining. w/ @m_finzi, @KuangYilun, @timrudner @micahgoldblum, @andrewgwils arxiv.org/abs/2312.17173 1/N
31K
Sanae Lotfi
@LotfiSanae
Jul 31, 2024
Excited and honored that our new work on token-level generalization bounds for LLMs won a Best Paper Award @tf2m_workshop at ICML! We investigate generalization in LLMs, e.g., memorization vs. reasoning, through compression bounds at the LLaMA2-70B scale. A 🧵, 1/8
17K
Sanae Lotfi
@LotfiSanae
Nov 29, 2022
🚨#NeurIPS2022 poster today: 4-6pm, Hall J #306🚨 Why do CNNs generalize so much better than MLPs? Why can neural networks fit random labels and still generalize? What is the value of encoding invariances in our models? arxiv.org/abs/2211.13609 1/N
arxiv.org
PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
While there has been progress in developing non-vacuous generalization bounds for deep neural networks, these bounds tend to be uninformative about why deep learning works. In this paper, we...
Sanae Lotfi
@LotfiSanae
Aug 24, 2023
We’re organizing Muslims in ML @NeurIPSConf this year 🥳 Submit a two-page abstract if you would like to showcase and present your work at the workshop by September 22 ⏰
Muslims in ML Workshop
@MuslimsinML
Aug 23, 2023
Excited to announce that the Muslims in Machine Learning (MusIML) workshop is back @NeurIPSConf! If you self-identify as Muslim, or work on research that address challenges faced by Muslims, we'd love to showcase your work. Submit an abstract by Sep 22: musiml.org/cfp/
26K
Sanae Lotfi
@LotfiSanae
Dec 15, 2024
I’m excited to be a keynote speaker and panelist at the machine learning and compression workshop @NeurIPSConf (neurips.cc/virtual/2024/w…). Find me in meeting room 211-214 at 1:25pm and 3:50pm to talk about compression bounds!
5.5K