Taisiya Glushkova retweeted
Had to try Jev, so I built a mood tracker where your writing stitches a flower. 🪡I🌸
As I type, Jev scores each sentence against 6 feelings.
The strongest supported feeling colours a section of the flower. 🫠
@typesafeai
Taisiya Glushkova retweeted
We’re at the dawn of neolabs. If you only paid attention to the @OpenAI (Astra) of the world, you’d miss the next @deepseek_ai moment or fail to anticipate @AnthropicAI's breakout year.
We built a Map to the Multi-Intelligence Universe to help anyone keep up with the frontier, to be in the know, to adapt, and to stay fit for survival 👇
Taisiya Glushkova retweeted
You only live once, so make sure to spend as much time as possible on your computer. You won’t have access to it when you die
Taisiya Glushkova retweeted
Excited to release AbstentionBench -- our paper and benchmark on evaluating LLMs’ *abstention*: the skill of knowing when NOT to answer!
Key finding: reasoning LLMs struggle with unanswerable questions and hallucinate!
Details and links to paper & open source code below!
🧵1/9
Taisiya Glushkova retweeted
This week, I'm attending #ICML2024. On Tuesday at 11:30 am, I will present our paper on generalized smooth variational inequalities. This is a joint work with Angelia Nedich and Lalitha Sankar.
Location: Hall C 4-9, poster number#1207.
Paper: openreview.net/pdf?id=4iBJyJ…
Taisiya Glushkova retweeted
The 14th Lisbon Machine Learning School #LxMLS kicked off last Thursday with nearly 200 participants! 🎉 Over the remaining 3 days, they will learn about transformers, vision & language, and causality from a range of outstanding speakers 👇
🔗 lxmls.it.pt/2024/
Amazing #LxMLS so far, with great talks by @mariotelfig @nlpnoah Slav Petrov @kchonyc! After the banquet and a free day to explore Lisbon, looking forward now to the next 3 days, with @danqi_chen @sarahookr Desmond Elliot @mohitban47 @adelehr @_albertgu.
Beyond happy to announce that I’ve completed my PhD! 🥳
Huge thanks to my committee members: @andre_t_martins, @KocmiTom, @MohitIyyer, João Magalhães, Luísa Coheur and José Borbinha!
Thank you for taking a chance on me. So glad I didn’t chicken out and committed to this journey. I’ve met so many passionate, inspiring, hardworking people who’ve shaped my view on research.
I’ll never forget the excitement and fear presenting my first paper at EMNLP 2021 😅
2
4
1,040
We at SARDINE lab are incredibly lucky to work in such a friendly, supportive and encouraging environment. I can’t imagine how much heart and effort it takes to build it this way. Thanks, @andre_t_martins, for making this experience so special.
1
10
685
Taisiya Glushkova retweeted
Tune in to our next ELLIS Lisbon & @Unbabel seminar to hear @KocmiTom from @Microsoft talk about "Navigating the Metrics Maze".
📅5th February, 5pm (WET)
🔗to join online tinyurl.com/3vn2zwud
🔗 for a list of upcoming talks and to subscribe tinyurl.com/4rb8mjyx
Taisiya Glushkova retweeted
I'm excited to be back in the classroom for CMU 11-711 Advanced NLP this semester! phontron.com/class/anlp2024/
We revamped the curriculum to take into account recent advances in LLMs, and we have a new assignment "build-your-own-LLaMa".
We'll be posting slides/videos going forward.
Taisiya Glushkova retweeted
Super excited about the Tower LLM we just released! It surpasses all open LLMs of the same size and larger (ALMA 13b, LLaMA 70b, Mixtral, etc.) on translation related tasks. Models, data, and evaluation benchmarks are all released!
Introducing Tower our cutting-edge multilingual #LLM for translation-related tasks! 🚀
With 7B parameters and support for 10 languages, Tower dominates in pre-translation tasks and machine translation. 🌎
Explore the future of #NLP now 👉 hubs.li/Q02g7_9B0


































