Yurii Paniv🇺🇦 retweeted
Today, among the goods that are universally intended for everyone, we must also include new forms of property, such as patents, algorithms, digital platforms, technological infrastructure and data. In a context where the wealth of nations depends increasingly on knowledge and technology, when these goods remain concentrated in the hands of a few, without adequate forms of sharing and access, a new imbalance is created that contradicts the universal destination of goods. In turn, it widens the gap between the included and the excluded, between those who can participate in the digital revolution and those who remain on the margins. #MagnificaHumanitas
Yurii Paniv🇺🇦 retweeted
🌍Introducing BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data!
LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data
We extend this effort to 45 new languages!
Yurii Paniv🇺🇦 retweeted
Can LLMs pass the Ukrainian ZNO test?
Find out in aclanthology.org/2025.unlp-1…
#unlpworkshop2025 #ACL2025 #ACL2025NLP #UNLPWorkshop
Yurii Paniv🇺🇦 retweeted
why is @OpenAI trippin about poached talent when they can just replace these researchers with GPT-5 agents
Yurii Paniv🇺🇦 retweeted
Nous Research announces the pre-training of a 15B parameter language model over the internet, using Nous DisTrO and heterogeneous hardware contributed by our partners at @Oracle, @LambdaAPI, @NorthernDataGrp, @CrusoeCloud, and the Andromeda Cluster.
This run presents a loss curve and convergence rate that meets or exceeds centralized training.
Our paper and code on DeMo, the foundational research that led to Nous DisTrO, is now available (linked below).
Yurii Paniv🇺🇦 retweeted
We are thrilled to announce the Interspeech 2025 URGENT Challenge, starting on 11/15!
Join us in building universal speech enhancement models to tackle in-the-wild speech data using large-scale, multilingual data. Details: urgent-challenge.github.io/u…
Super cool to share my PhD research proposal as a NotebookLM podcast!
youtube.com/watch?v=dzN3uJxn…
Arxiv paper: arxiv.org/abs/2410.07880
Yurii Paniv🇺🇦 retweeted
Шановні пані та панове!
Моя кохана дружина разом з @ucu_apps організовує літній онлайн-курс з продуктової аналітики. ДУЖЕ великий плюс цього курсу полягає в тому, шо весь прибуток з курсу піде на проект Starlinks 202 від @dzygaspaw – на Старлінки для Сил Оборони 🤝
Yurii Paniv🇺🇦 retweeted
New English to Ukrainian translation finetune that generalizes to any to Ukrainian, proud to ship with @robinhad @dchaplinsky @NikitaTrynus
Check it out: huggingface.co/lang-uk/drago…
State-of-the-art machine translation from English to Ukrainian 🔥🔥🔥
Data and models are openly available!
aclanthology.org/2024.unlp-1…
#unlpworkshop #lrec2024
our paper 🎉
with @dchaplinsky @darkproger @NikitaTrynus
State-of-the-art machine translation from English to Ukrainian 🔥🔥🔥
Data and models are openly available!
aclanthology.org/2024.unlp-1…
#unlpworkshop #lrec2024
Yurii Paniv🇺🇦 retweeted
Replying to @jbhuang0604
that’s actually just it. they took transformers and scaled them up again. i have been saying it for a year now that all the ingredients are there.
до речі підписуйтесь на мій телеграм-канал t.me/pehade_blog, де я розказую як проходить навчання на PhD в УКУ на комп'ютерних науках
Yurii Paniv🇺🇦 retweeted
До уваги всіх дата саєнтистів!
Відкрився україномовний Discord сервер як альтернатива нашим групам у Telegram.
👉🏻 Долучайтесь прямо зараз — discord.gg/nmUCXz55
Yurii Paniv🇺🇦 retweeted
Happy to release Accelerated Scan, a kernel library for first order parallel associative scans in vanilla @PyTorch, Triton 2.2.0 and CUDA C++.
pip install accelerated-scan🧵
Yurii Paniv🇺🇦 retweeted
Two esteemed conferences in the #NLP and #AI sphere, #EMNLP (@emnlpmeeting) & #ACL (@aclmeeting), have expressed no objections to the participation of researchers from sanctioned Russian State entities involved in weapon development used against Ukrainians in their events. (1/10)




























