iiinova — where your digital self keeps evolving

Reposted by Hanna Yukhymenko

Vilém Zouhar @zouhar.bsky.social · 17/07/2026

There are many things machine translation still can't do. Help us steer the next direction by contributing hard-to-translate inputs (and be on a cool paper).

2148

Reposted by Hanna Yukhymenko

Apertus @apertusllm.bsky.social · 24/07/2026

Available now! Apertus 1.5 — 8B & 70B models with multimodal text/image/audio input, a 4x longer context window, optional thinking mode, and improved tool use, all built transparently and responsibly. 3.2M+ downloads 🚀 #Apertus #OpenSourceLLM Details+Links+Open roles: apertus-ai.org/articles/202...

Geometric shapes with Apertus 1.5 announcement and EPFL / ETH / CSCS logos.

295

Reposted by Hanna Yukhymenko

Vilém Zouhar @zouhar.bsky.social · 06/07/2026

All my homies left for ACL/ICML and left me home managing a project *for which we're looking for coauthors* 🥸. Join us (also talk to @sethjsa.bsky.social @onadegibert.bsky.social @niyatibafna.bsky.social @patuchen.bsky.social @michellewastl.bsky.social @ayukh.bsky.social)

2104

Hanna Yukhymenko @ayukh.bsky.social · 25/03/2026

Very excited to show you my favourite poster at #EACL2026 in Rabat🇲🇦 MME Workshop! Come visit us on Saturday 4:50PM to yap about problems of multilingual benchmarks and how can we try to solve them with improved translation 👀

021

Reposted by Hanna Yukhymenko

Samuel Simko @samuelsimko.bsky.social · 25/07/2025

Excited to be joining #ACL2025NLP in Vienna 🇦🇹! DM me if you would like to meet up and chat 👋

041

Reposted by Hanna Yukhymenko

ETH CS Department @csateth.bsky.social · 24/04/2025

A powerful step for linguistic tech: ETH Zurich student Hanna Yukhymenko developed MamayLM – a Ukrainian #LLM fluent in 🇺🇦 & 🇬🇧, capturing language, culture & history. Supervised by Prof. Vechev & alumnus A. Alexandrov, in collab with INSAIT. bit.ly/3ED4o5k @ayukh.bsky.social @ethzurich.bsky.social

bit.ly

Announcing MamayLM, an efficient state-of-the-art Ukrainian LLM

A Blog post by Institute for Computer Science, Artificial intelligence and Technology on Hugging Face

031

Reposted by Hanna Yukhymenko

Olga Ovcharenko @oovcharenko.bsky.social · 12/12/2024

📢 Our benchmark on self-supervised learning for single-cell data🧬 is accepted at the #NeurIPS2024 SSL workshop. We take a first step towards establishing best practices for SSL methods for single-cell data, and benchmark 8 SSL methods on 3 downstream tasks across 8 datasets.

161

Hanna Yukhymenko @ayukh.bsky.social · 07/12/2024

Watch me stalk Kaggle in Vancouver to get stickers

100

Reposted by Hanna Yukhymenko

Sara Hooker @sarahooker.bsky.social · 05/12/2024

Is MMLU Western-centric? 🤔 As part of a massive cross-institutional collaboration: 🗽Find MMLU is heavily overfit to western culture 🔍 Professional annotation of cultural sensitivity data 🌍 Release improved Global-MMLU 42 languages 📜 Paper: arxiv.org/pdf/2412.03304 📂 Data: hf.co/datasets/Coh...

75912

Hanna Yukhymenko @ayukh.bsky.social · 04/12/2024

Цей день настав - Ukrainian is finally recognized as a mid-resource language 🇺🇦🦅🦅🦅

100

Hanna Yukhymenko @ayukh.bsky.social · 29/11/2024

Exciting end of the year! - Won the GraySwanAI jailbreaking challenge for harmful code generation - Proud Ukrainian ambassador for Cohere4AI new Aya Expanse models - Started my master thesis👩‍🍳🇺🇦👀 - Going to Vancouver🇨🇦 for @neuripsconf.bsky.social to chat about LLM privacy and SynthPAI #neurips

020

Hanna Yukhymenko @ayukh.bsky.social · 28/11/2024

Seems to be a hot take here: why are people getting mad about stuff they post *themselves* online? Your posts online are getting scraped all the time and you chose an open-source movement leader as a scapegoat. Just initiate a discussion with HF about the "right to be forgotten" from GDPR

010

Reposted by Hanna Yukhymenko

maksym.eristavi @maksymeristavi.com · 18/11/2024

Zaporizhzhia, a big Ukrainian city of almost one million, is under a massive drone attack. terrorism is russian culture.

11263116

Hanna Yukhymenko @ayukh.bsky.social · 12/12/2023

One year of ChatGPT has shown incredible capabilities of LLMs. However, they still have lots of problems! The LVE project aims at addressing this - with LVEs we track LLM vulnerabilities and exposures in an open-source community-first approach. Contribute and more info: lve-project.org #NLP #LLM

lve-project.org

LVE Repository

We document and track vulnerabilities and exposures of large language models (LVEs).

050

Reposted by Hanna Yukhymenko

Укртвізалізниця @uabluerail.org · 26/05/2023

Тред з корисними порадами для тих, хто щойно долучився. 🧵

601233352

Hanna Yukhymenko @ayukh.bsky.social · 09/07/2023

Купила українські вареники в Швейцарії

110