Vivek Iyer
@remorax98
AI/ML Intern at | PhD @EdinburghNLP 🏴 | Apple AI/ML Scholar 2025 | Interested in Multilingual & Multicultural NLP! 🌍
Are you compositionally curious 🤓 Want to know how to learn embeddings using🌲? In our new #ICML2025 paper, we present Banyan: A recursive net that you can train super efficiently for any language or domain, and get embeddings competitive with much much larger LLMs 1/🧵
Carlos Alcaraz. Jannik Sinner. The gentlemen's singles final will be box office 🍿 #Wimbledon
Glad I can finally share this publicly: I'm happy to share I'm one of the recipients of the 2025 Apple Scholars in AI/ML PhD fellowship! Please find the full list here: machinelearning.apple.com/updates/apple-… Privileged to be part of such a talented cohort, and working with such an experienced…
Thrilled to share our #NAACL paper on automatic evaluation of image transcreation - a creative and future-facing #NLP task! Grateful for the amazing collab with @simi_97k and @gneubig of CMU :) If you're into #GenerativeAI or evaluating creative tasks, check it out:…
We've talked a lot about evaluation in MT, but how do we evaluate related creative tasks like transcreation? 🔍💡 For eg. in Zootopia (2016), while the newscaster was a moose in the US, it was transcreated to a panda in China, a koala in Australia and a jaguar in Brazil. How…
Hi everyone, I’m excited to share I’ll be doing two consecutive six-month internships this year: first with @Apple in Pittsburgh, USA (March-Aug) and then with @AIatMeta in Paris, France! (Aug-Feb) At Apple, I’ll be advised by Liling Tan (@alvations) and the amazing team at Apple…
Introducing LMUnit: Natural language unit testing for LLM evaluation How do you really know if your language model is behaving the way you expect? When evaluation is this critical, your best methodology shouldn't just be vibes. With SOTA results on FLASK & BigGenBench and…
Today we release EuroLLM-9B: the best EU-made multilingual LLM of its size! Check the blog post for more info and results: huggingface.co/blog/eurollm-t…. Stay tuned for the technical report and bigger and more powerful models!
After going to NAACL, ACL and #EMNLP2024 this year, here are a few tips I’ve picked up about attending *ACL conferences. Would love to hear any other tips if you have them! 🙂 1. This might be obvious, but I suggest showing everyone the same respect and interest regardless of…
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…
#EMNLP2024 Best Paper 1/5: An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance
#EMNLP2024 Best Paper 1/5: An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance
Happy to share we won a Featured Presentation (Spotlight) slot at WMT for this work :) Grateful for the opportunity! If you're in Miami, please do attend our presentation on Nov 15th www2.statmt.org/wmt24/program.…
We know LLMs are poor at MT in low-resource languages (LRLs): curious how to adapt them to perform better? 🚀 Our new paper explores the interplay between scale (of MT data) and diversity (of tasks/langs) in instruction tuning in determining LLM-MT performance for LRLs💡…