Simran Khanuja (@simi

Simran Khanuja

553 posts

Simran Khanuja

@simi_97k

NLP | PhD Student @LTIatCMU | Predoctoral Researcher @Google | Microsoft Research | BITS Pilani

simran-khanuja.github.io

Joined April 2018

Pinned
Simran Khanuja
@simi_97k
Nov 14, 2024
Thank you so much @emnlpmeeting for this wonderful recognition! I’m so honored and humbled 💕 Thanks @gneubig for your support throughout! We’ve been working on this for 1.5 years and everyone who has spoken with me in the recent past knows how passionately I feel about this
62K
Simran Khanuja
@simi_97k
May 13, 2025
Excited to join @GoogleDeepMind as a student researcher with @lunwang1996 for the summer! I’ll be in the Bay Area, MTV Campus. Would love to meet folks around here! Please DM if you’d like to catch up :)
31K
Simran Khanuja
@simi_97k
Apr 9, 2022
Ecstatic to share that I'll be joining @SCSatCMU for my PhD at LTI this Fall! I'll be working with @gneubig and @dan_fried among many others! I've really enjoyed talking to students and faculty at CMU and am very excited to embark on this journey✨ (1/n)
Simran Khanuja
@simi_97k
Apr 2, 2024
Ever noticed how Pixar adapts movies for international markets? The beloved newscaster in Zootopia is a jaguar in Brazil, a panda in China, a koala in Australia … While machine translation (MT) has only dealt with language in speech/text thus far, we extend the scope of MT to
55K
Simran Khanuja
@simi_97k
Nov 16, 2023
How would you choose the best data instances to label, that maximize the performance of a model on target data? What if your target data is multilingual and you have no annotators in those languages? Our new work, DeMuX, addresses this problem. arxiv.org/abs/2311.06379 (1/n)
arxiv.org
DeMuX: Data-efficient Multilingual Learning
We consider the task of optimally fine-tuning pre-trained multilingual models, given small amounts of unlabelled target data and an annotation budget. In this paper, we introduce DEMUX, a...
37K
Simran Khanuja
@simi_97k
Sep 23, 2024
This work has been accepted to EMNLP '24 (Main)❤️ Check out our project page: machine-transcreation.github.io/image-transcre… I've given talks on this work and future directions at Pinterest, Edinburgh, and Google (thanks for the invites!): docs.google.com/presentation/d… I was also fortunate to present a
18K
Simran Khanuja
@simi_97k
Mar 25, 2022
It was great meeting with undergrad students passionate about research at BITS-Goa! In the last couple of years, they've successfully setup research groups like LRG, SAiDL etc., significantly enhancing the research culture on campus. (1/2)
Simran Khanuja
@simi_97k
Jan 22, 2023
Grateful to have received the best paper award at SLT 2022 for FLEURS! FLEURS is a multi-lingual (102 languages), multi-modal (speech-text), n-way parallel dataset, built on top of Flores-101. (1/n)
Alexis Conneau
@alex_conneau
Jan 13, 2023
Our FLEURS paper won the best paper award at SLT 2022! @ieee_slt SLT: slt2022.org/best-papers.php arXiv: arxiv.org/abs/2205.12446 Thanks to the organizers! Grateful for the collaboration with many great colleagues 🙂
21K
Simran Khanuja
@simi_97k
Jul 27, 2025
So excited to be one of the five winners of the Imminent Translated Research Grants! This is for work done with @OpenNLPLabs @gneubig @Diyi_Yang @zhangyt0704 We've built an image transcreation platform that enables translators to culturally localize images using simple text
Translated.
@Translation
Jul 24, 2025
Introducing the winners of the 4th edition of the Imminent Research Grants! Through Imminent, we support researchers exploring new frontiers in language & AI. This year’s selected projects take thoughtful approaches to timely topics from localizing multimodal content with
00:00
drive.google.com
Anonymous Platform Demo.mp4
13K
Simran Khanuja
@simi_97k
Mar 14, 2024
Now accepted to NAACL 2024 ❤️ Excited to present this in Mexico City and continue building upon this work🎊
Simran Khanuja
@simi_97k
Nov 16, 2023
How would you choose the best data instances to label, that maximize the performance of a model on target data? What if your target data is multilingual and you have no annotators in those languages? Our new work, DeMuX, addresses this problem. arxiv.org/abs/2311.06379 (1/n)
12K
Simran Khanuja
@simi_97k
May 7, 2021
Since multilingual LMs cannot equitably represent a 100+ languages, we have recently witnessed the growth of a language/domain specific pre-trained model universe. In our ACL 2021 Findings paper, we make a first attempt at merging multiple pre-trained LMs using KD. (1/2)
Simran Khanuja
@simi_97k
Mar 22, 2021
Excited to share a technical write-up on MuRIL, now available on arxiv! arxiv.org/abs/2103.10730
Simran Khanuja
@simi_97k
Nov 16, 2024
Hopping on the trend: I'm also looking for summer internships for 2025, focusing on geo-cultural diversity of vision-language models (or image transcreation if anyone is working on it 😌). Please feel free to check out my website (simran-khanuja.github.io) and DM/email
26K
Simran Khanuja
@simi_97k
Dec 11, 2023
I recently gave a lecture on Image-Text Modeling for Multilingual NLP at CMU and thought I'd share my slides in case interested folks may find it useful! drive.google.com/file/d/1iHrnC1… Here are a few things covered in the slides. (1/n)
drive.google.com
Image-Text Modeling for Multilingual NLP.pdf
12K