Antonis Anastasopoulos
@anas_ant
Followers
3K
Following
12K
Media
116
Statuses
1K
Assist. Prof at George Mason CS #nlproc MT, ASR, and documentation of endangered languages.
Fairfax, VA
Joined November 2012
🎉Check out our recent papers accepted to #NeurIPS and #EMNLP on #MechInterp of LLMs (I'm hiring Fall'26 PhDs on this topic) #NeurIPS2025 Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
3
13
116
Multilingual representation alignment through images (and without parallel data for new languages) : check out Nate's work #ACL2025NLP tomorrow. Paper: https://t.co/9g1icD95kL More details: 👇
aclanthology.org
Nathaniel Krasner, Nicholas Lanuzo, Antonios Anastasopoulos. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2025.
Can multilingual text encoders borrow the semantic space from images to align their representations cross-lingually? I am presenting my paper “Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning” at the 4pm poster session at ACL tomorrow! 🧵 (1/9)
0
1
14
Join the Birds-of-a-Feather meetup on Language Technologies for Crisis Response and Preparedness at #ACL2025NLP this Wednesday, to discuss research with real-world impact!
I'm attending #ACL in Vienna this week. 🇦🇹 We're running a BoF on Language Technologies for Crisis Response and Preparedness, co-hosted w/Will Lewis from @UWlinguistics 📆 Wed. 30th, 11am. Room 1.33. You can join us virtually too. DM me if you’re interested ✨
0
0
11
Why this matters: Even with great tech, human-in-the-loop design is essential. Extending our previous work on LLM efficacy, our results help guide responsible use of LLMs in expert coding workflows, especially in sensitive domains like education.
1
1
2
💡Can LLMs speed up expert coding without skewing their judgment? We explore the trade-offs of AI-assisted topic modeling in education research, where speed, cost, and bias all matter. 🧾Presenting our work at #ACL2025 in Vienna! 🗓️BEA Workshop Poster Session B 📍Friday, Aug 1st
1
1
4
Check out this cool dialect-related work at #ACL2025NLP next week, if you're in Vienna!
How can we make models understand dialectal input, even in dialects with very little data available? Our work indicates that Rule-Based Normalization can significantly help. If you're at #ACL2025, check out our poster on Monday at 6pm! https://t.co/sU2BQb6L3o 1/4
0
3
19
Looking forward to this year's edition! With great speakers: Ryan McDonald @yulanhe Vlad Niculae @anas_ant @raquel_dmg @annargrs @preslav_nakov @mohitban47 @eunsolc @MarieMarneffe !
📢 10 Days Left to apply for the AthNLP - Athens Natural Language Processing Summer School! ✍ Get your applications in before June 15th! https://t.co/2D4hlmXvsn
1
12
24
📣 Call for Participation EXTENDED to Sunday 15 June for the @AthensNLP 2025! 📍 4–10 September 2025 | NCSR Demokritos, Athens 📄 Apply & view the full program: https://t.co/2D4hlmXvsn
#NLP #AI #SummerSchool #NaturalLanguageProcessing #AthNLP2025
0
8
4
📢 CFP announced for the Athens #NaturalLanguageProcessing #SummerSchool! Are you passionate about #NLP and #MachineLearning? Join us in Athens 4–10 Sept @NCSR_Demokritos for talks, hands-on labs & top domain experts! 📅Apply by 30 May! https://t.co/2D4hlmXvsn
#AthNLP2025 #AI
0
7
6
📢 I am looking for a postdoc for the next academic year! (Due to the funding source, US persons preferred) Interested in multimodal LLMs and their application to education domains (plus multilinguality, cross-lingual, and low-resource learning)? Contact me here/email if yes!
0
13
37
Hi all, Do you have a reviewed ARR paper on speech translation to commit to @iwslt ? @iwslt has enabled paper commitment for fully reviewed papers from ARR for 2025. If you'd like to commit your paper, please fill out this form by May 17, 2025: https://t.co/qEFbvdx5VK
docs.google.com
To commit fully-reviewed reviewed ARR papers to IWSLT 2025, please provide the unique identifier of the ARR submission on OpenReview, and contact information for the submission. The paper identifier...
0
4
8
Congratulations to @aarsri21 on winning the Best Paper Award at W-NUT at NAACL 2025! This paper applies various interventions simulating noisy text or dialectal variation to discover how different interventions have different effects.
2
4
24
Presenting this at #WACV2025 today + oral session tomorrow. Come say hi if you are around!
🧵1/ New Paper! 🚀 Our latest work with @anas_ant and @ZzwWilliam is now on arXiv. https://t.co/eaJH1FFrJq! We look at cultural understanding in LLMs and develop an approach for automatically updating the culture represented in images. Thread 🧵⬇️
1
1
3
Why participate? ✨Low-resource is truly the frontier, and there are many ways to making an impact for a language community: from providing a dataset for a language that is missing one, to exploring the limits of different models and techniques.
0
3
5
🆕 This year includes new and more diverse language pairs (e.g. Fongbe to French, Estonian to English) in addition to continuing pairs 🆕🔊 Also new this year is a *data track* which encourages the creation of new speech translation datasets for less-supported languages
1
3
4
Today's task: Low-resource ST! 🎯 Goal: Building speech translation models for currently underserved, mostly low-resource languages and varieties 🗓️ This is the 5th iteration, with new and continuing language pairs (10 total!) 🔗:
iwslt.org
Home of the IWSLT conference and SIGSLT.
1
3
6
.@Mason_CEC professor receives an NSF CAREER Award for his work on privacy and data security. Discover more⬇️ #MasonNation
https://t.co/IzAqagrOoB
gmu.edu
Evgenios Kornaropoulos received a National Science Foundation (NSF) CAREER award for $648,811 for work on privacy and data security under the title “Encrypted Systems with Fine-Grained Leakage.”
0
6
8
We are excited to announce the launch of ML SUPERB 2.0 ( https://t.co/YAASYyVHtv) as part of the Interspeech 2024 official challenge! We hope this upgraded version of ML SUPERB advances universal access to speech processing worldwide. Please join it! #Interspeech2025
0
22
67
The curtains are about to rise in just 2 hours! 🎉 Get ready for an exciting lineup at today's WiNLP Workshop. Stay tuned !
0
4
11
Stop by Jasmine #20 right now to see how @iamshnoo and @chahatsaidit explore multimodal LLMs to uncover the implicit associations they make in their BiasDora work
3
4
58