Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
Paper • 2605.06643 • Published • 4
ETH Zurich
university
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography
hdong51
submitted a
paper to Daily Papers 19 days ago
jw-sohn
submitted a
paper to Daily Papers about 1 month ago
mdmoor
submitted a
paper to Daily Papers about 1 month ago
docs: fill in dataset card sections (bias, limitations, curation rationale)
#6 opened 3 months ago
by 
samtuckervegan
MatteoFasulo
authored a
paper 3 months ago
hannayukhymenko
submitted a
paper to Daily Papers 3 months ago
hannayukhymenko
posted an update 3 months ago
Post
2083
Do you translate your benchmarks from English correctly? 🤔
Turns out, for many languages it is much harder than you can imagine!
Introducing Recovered in Translation 🌍 together with @aalexandrov
https://ritranslation.insait.ai
Translating benchmarks is a painful process, requiring a lot of manual inspection and adjustments. You start from setting up the whole pipeline and adapting to every format type, including task specifics. There already exist some massive benchmarks, but they still have some simple (and sometimes silly) bugs, which can hurt the evaluations :( We present a novel automated translation framework to help with that!
Eastern and Southern European languages introduce richer linguistic structures compared to English and for benchmarks which heavily rely on grammatical coherence machine translation presents a risk of harming evaluations. We discover potential answer leakage or misleading through grammatical structure of the questions. Some benchmarks are also just outdated and need to be retranslated with newer and better models.
We present a framework with novel test-time scaling methods which allow to control time and cost investments, while at the same time mitigate the need for human-in-the-loop verification. While working on Ukrainian-focused MamayLM models, we had to translate 10+ benchmarks in a short span of time. Finding human evaluators is costly and time-consuming, same goes for using professional translators. With our pipeline we were able to do it in 3 days🏎️
We hope our findings will help enable stronger multilingual evaluations and developments. We release all produced benchmarks on Hugging Face together with the source code and Arxiv paper 🤗
Paper: Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets (2602.22207)
Code: https://github.com/insait-institute/ritranslation
Benchmarks: https://huggingface.co/collections/INSAIT-Institute/multilingual-benchmarks
Turns out, for many languages it is much harder than you can imagine!
Introducing Recovered in Translation 🌍 together with @aalexandrov
https://ritranslation.insait.ai
Translating benchmarks is a painful process, requiring a lot of manual inspection and adjustments. You start from setting up the whole pipeline and adapting to every format type, including task specifics. There already exist some massive benchmarks, but they still have some simple (and sometimes silly) bugs, which can hurt the evaluations :( We present a novel automated translation framework to help with that!
Eastern and Southern European languages introduce richer linguistic structures compared to English and for benchmarks which heavily rely on grammatical coherence machine translation presents a risk of harming evaluations. We discover potential answer leakage or misleading through grammatical structure of the questions. Some benchmarks are also just outdated and need to be retranslated with newer and better models.
We present a framework with novel test-time scaling methods which allow to control time and cost investments, while at the same time mitigate the need for human-in-the-loop verification. While working on Ukrainian-focused MamayLM models, we had to translate 10+ benchmarks in a short span of time. Finding human evaluators is costly and time-consuming, same goes for using professional translators. With our pipeline we were able to do it in 3 days🏎️
We hope our findings will help enable stronger multilingual evaluations and developments. We release all produced benchmarks on Hugging Face together with the source code and Arxiv paper 🤗
Paper: Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets (2602.22207)
Code: https://github.com/insait-institute/ritranslation
Benchmarks: https://huggingface.co/collections/INSAIT-Institute/multilingual-benchmarks
- 1 reply
hannayukhymenko
authored a
paper 3 months ago
XiangZ
submitted a
paper to Daily Papers 5 months ago
MatteoFasulo
authored a
paper 5 months ago
yuanwenyue
submitted a
paper to Daily Papers 5 months ago
dvruette
submitted a
paper to Daily Papers 5 months ago
Zixiang-Zhao
authored a
paper 7 months ago
hannayukhymenko
posted an update 9 months ago
Post
3099
Releasing the Jupyter Agent Dataset! 🚀
Built from 7 TB of real Kaggle datasets + 20k notebooks, creating real code exec traces using Qwen3-Coder and E2B.
Training on this data dramatically improves the ability to execute code and analyze data.
We (@baptistecolle @hannayukhymenko @lvwerra ) have created a novel synthetic data generation pipeline with efficient scaffolding, which gives a big performance boost after training your coding agent🔥With the help of real Kaggle notebooks and datasets we generate synthetic notebooks which aim to analyze datasets and answer factual questions about them more efficiently. We simulate a real code execution environment by prompting LLMs or with the help of E2B sandboxes. We have built a dataset of 50k+ high-quality LLM-generated notebooks which can help your agent become better at performing data analysis and question answering.
Link: https://huggingface.co/datasets/data-agents/jupyter-agent-dataset
Built from 7 TB of real Kaggle datasets + 20k notebooks, creating real code exec traces using Qwen3-Coder and E2B.
Training on this data dramatically improves the ability to execute code and analyze data.
We (@baptistecolle @hannayukhymenko @lvwerra ) have created a novel synthetic data generation pipeline with efficient scaffolding, which gives a big performance boost after training your coding agent🔥With the help of real Kaggle notebooks and datasets we generate synthetic notebooks which aim to analyze datasets and answer factual questions about them more efficiently. We simulate a real code execution environment by prompting LLMs or with the help of E2B sandboxes. We have built a dataset of 50k+ high-quality LLM-generated notebooks which can help your agent become better at performing data analysis and question answering.
Link: https://huggingface.co/datasets/data-agents/jupyter-agent-dataset
- 3 replies
MatteoFasulo
authored a
paper 10 months ago
Tianfwang
authored 4
papers about 1 year ago
DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control
Paper • 2312.03048 • Published • 1
Consistency^2: Consistent and Fast 3D Painting with Latent Consistency Models
Paper • 2406.11202 • Published • 3
Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation
Paper • 2412.07761 • Published
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis
Paper • 2505.09358 • Published • 27
hannayukhymenko
posted an update about 1 year ago
Post
3686
🚀 We are delighted to announce MamayLM, a new state-of-the-art efficient Ukrainian LLM!
📈 MamayLM surpasses similar-sized models in both English and Ukrainian, while matching or overtaking up to 10x larger models.
📊 MamayLM is a 9B model that can run on a single GPU, enabling cost-efficient AI autonomy and adoption across sectors in Ukraine such as education, legal, healthcare, public services and others (e.g., by specializing it to particular use cases). MalayLM is also attractive for organizations wishing to preserve data privacy as it s efficiency allows it to run on a local machine.
🧠 MamayLM is trained on high-quality Ukrainian data and understands Ukrainian language, culture, and history. It is built on top of Google’s Gemma 2 9B model, but uses a number of new advances stemming from INSAIT’s experience in creating BgGPT, a Bulgarian LLM we released last year, now adopted nationwide and profiled several times by Google as a worldwide success case.
🤝 MamayLM is developed in a collaboration between researchers at INSAIT and ETH Zürich and is trained entirely via donations to INSAIT for AI compute resources.
📥 MamayLM is now freely available to download on INSAIT’s HuggingFace in both full and quantized versions. We also publicly release all Ukrainian benchmarks we evaluated on.
📝 Further, we release blog posts in both English and Ukrainian, sharing our approach to creating MamayLM, hoping to drive further improvements by the community.
🌎 The release of LLMs for various languages is part of INSAIT’s mission in ensuring countries can achieve AI autonomy in a cost-efficient, controlled, safe and predictable manner.
MamayLM model and benchmarks:
INSAIT-Institute
Blog (EN): https://huggingface.co/blog/INSAIT-Institute/mamaylm
Blog (UKR): https://huggingface.co/blog/INSAIT-Institute/mamaylm-ukr
📈 MamayLM surpasses similar-sized models in both English and Ukrainian, while matching or overtaking up to 10x larger models.
📊 MamayLM is a 9B model that can run on a single GPU, enabling cost-efficient AI autonomy and adoption across sectors in Ukraine such as education, legal, healthcare, public services and others (e.g., by specializing it to particular use cases). MalayLM is also attractive for organizations wishing to preserve data privacy as it s efficiency allows it to run on a local machine.
🧠 MamayLM is trained on high-quality Ukrainian data and understands Ukrainian language, culture, and history. It is built on top of Google’s Gemma 2 9B model, but uses a number of new advances stemming from INSAIT’s experience in creating BgGPT, a Bulgarian LLM we released last year, now adopted nationwide and profiled several times by Google as a worldwide success case.
🤝 MamayLM is developed in a collaboration between researchers at INSAIT and ETH Zürich and is trained entirely via donations to INSAIT for AI compute resources.
📥 MamayLM is now freely available to download on INSAIT’s HuggingFace in both full and quantized versions. We also publicly release all Ukrainian benchmarks we evaluated on.
📝 Further, we release blog posts in both English and Ukrainian, sharing our approach to creating MamayLM, hoping to drive further improvements by the community.
🌎 The release of LLMs for various languages is part of INSAIT’s mission in ensuring countries can achieve AI autonomy in a cost-efficient, controlled, safe and predictable manner.
MamayLM model and benchmarks:
Blog (EN): https://huggingface.co/blog/INSAIT-Institute/mamaylm
Blog (UKR): https://huggingface.co/blog/INSAIT-Institute/mamaylm-ukr
- 1 reply