@phalgooon For the conditions of the Ladakh, the Himalayan is the best bike. It has been heavily tested.
Do you drive frequently and which bike do you use normally?
@ycocerious Firstly, good job Punarv 👏👏. Just wanted to let you know that I'm not able to install the app from the landing page on clicking 'Install on Android'. It could be an issue in my phone, not sure.
ACL2024 (@aclmeeting) paper posts. If you are attending ACL in person, then please do drop by.
Paper #1:
🚀 Excited to share our research paper: "An Empirical Study of In-context Learning in LLMs for Machine Translation", which we'll be presenting at ACL 2024!
📄Paper: https://t.co/OrOh57ueAh
🛠️Github: https://t.co/gmZz7LOaxr
🗓️Slides: https://t.co/JqZxzunFg4
▶️Video: https://t.co/tOzZcLVbKZ
Our work delves into the ICL capabilities of LLMs for MT, including focusing on how different aspects of demonstration impact performance.
joint work w/ @jaygala24@pranjalchitale
I will be attending @aclmeeting#ACL2024 in person in Thailand.
If you are interested in Multilinguality (evaluation/meta-evaluation/LLMs/Machine Translation), Efficient Methods in NLP, do reach out for a chat.
Looking forward to meeting the community!
📣 📣 📣 New instruction-tuned LLM! 📣 📣 📣
Today, we announce an initial release of "Airavata", an instruction-tuned LLM for Hindi.
Blog: https://t.co/JtmVZIpVS9
Model: https://t.co/MVpTA0UWEZ
Datasets: https://t.co/avtGcvYT2v
(1/N)
🚨🚨🚨 Romanization Based Multilingual LLM Adaptation Technique
Presenting "RomanSetu", a technique to exploit Romanization to efficiently unlock or bridge the multilingual capabilities of LLMs like LLaMA. Setu means bridge in Hindi.
https://t.co/W4nZQWnpvU
It was almost 10 months since I posted by first tweet:
https://t.co/HCTf5rl2D7
And now, we finally were able to do it (a late post though). Do check out our ported IndicTrans2 and IndicTrans2-Distilled models on HuggingFace.
@jaygala24@pranjalchitale @prajdabre1
I am extremely pleased to announce that IndicTrans2 will be published in TMLR (@TmlrOrg). This is a tremendous achievement for my coauthors and me that took nearly 1.5 years of hard work. The camera ready version will be out soon but for now we are over the moon!
#NLProc#ACL
Led my first work at @MSFTResearch where we build upon amazing work done on MEGA and introduce MEGAVERSE, where we benchmark new tasks and languages on state-of-the-art commercial and open-source models. (1/n)
We learn a regression model, CTQ Scorer (Contextual Translation Quality), which selects examples based on multiple features to maximize machine translation quality in few-shot prompting.