DISCO: Document Intelligence Suite for COmparative Evaluation
Paper • 2603.23511 • Published
AI & ML interests
None defined yet.
Recent Activity
kenza-ily
authored a
paper 9 days ago
Reubencf
authored a
paper 13 days ago
Post
6446
We should really have a release date range slider on the /models page. Tired of "trending/most downloaded" being the best way to sort and still seeing models from 2023 on the first page just because they're embedded in enterprise pipelines and get downloaded repeatedly. "Recently Created/Recently Updated" don't solve the discovery problem considering the amount of noise to sift through.
Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.
Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.
- 3 replies
kenza-ily
authored 2
papers 29 days ago
kenza-ily
authored a
paper 30 days ago
Post
2703
🚀 I am thrilled to announce the release of a new Konkani LLM!
We've seen some fantastic results for both translation and transliteration tasks, and I'm excited to share this progress with the community.
📖 Read the launch article and see the results: https://huggingface.co/blog/Reubencf/konkani-llm
🤖 Explore the model and collection:
konkani
I would love to hear your feedback or see what you build with it! #Konkani #LLM #NLP #HuggingFace #IndicNLP #Konkani
We've seen some fantastic results for both translation and transliteration tasks, and I'm excited to share this progress with the community.
📖 Read the launch article and see the results: https://huggingface.co/blog/Reubencf/konkani-llm
🤖 Explore the model and collection:
I would love to hear your feedback or see what you build with it! #Konkani #LLM #NLP #HuggingFace #IndicNLP #Konkani
hannayukhymenko
submitted a
paper to Daily Papers about 1 month ago
hannayukhymenko
posted an update about 1 month ago
Post
1987
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 about 1 month ago
Post
3494
🤔 Who would win ?
- a fully subsidized ai lab
- 3 random students named
kurakurai ?
demo : Tonic/fr-on-device
if you like it give the demo a little star and send a shoutout to : @MaxLSB @jddqd and @GAD-cell for absolutely obliterating the pareto frontier of the french language understanding .
- a fully subsidized ai lab
OR - 3 random students named
demo : Tonic/fr-on-device
if you like it give the demo a little star and send a shoutout to : @MaxLSB @jddqd and @GAD-cell for absolutely obliterating the pareto frontier of the french language understanding .
- 4 replies
Post
3337
🙋🏻♂️hello my lovelies ,
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
it is with great pleasure i present to you my working one-click deploy 16GB ram completely free huggingface spaces deployment.
repo : Tonic/hugging-claw (use git clone to inspect)
literally the one-click link : Tonic/hugging-claw
you can also run it locally and see for yourself :
docker run -it -p 7860:7860 --platform=linux/amd64 \
-e HF_TOKEN="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_TRUSTED_PROXIES="YOUR_VALUE_HERE" \
-e OPENCLAW_GATEWAY_PASSWORD="YOUR_VALUE_HERE" \
-e OPENCLAW_CONTROL_UI_ALLOWED_ORIGINS="YOUR_VALUE_HERE" \
registry.hf.space/tonic-hugging-claw:latest
just a few quite minor details i'll take care of but i wanted to share here first
- 2 replies
Cartinoe5930
authored a
paper about 2 months ago
azminetoushikwasi
submitted a
paper to Daily Papers 2 months ago
Post
2211
📢 New release! World_events Dataset now available featuring global events spanning 2023 through 2025
🌍 https://huggingface.co/collections/Reubencf/world-events
🚀 2026 dataset dropping soon
🌍 https://huggingface.co/collections/Reubencf/world-events
🚀 2026 dataset dropping soon
- 1 reply
Post
1898
Now Live: The Reubencf/Nano_Banana_Editor now includes 10 free requests/day! 🍌 I'm personally sponsoring these credits to help make open AI accessible to all.
(Note: Limits are subject to change based on funding).
Enjoy !
(Note: Limits are subject to change based on funding).
Enjoy !
Post
1076
TranslateGemma: Open Translation Models (Jan 2026)
Google introduces TranslateGemma, a new suite of open translation models based on Gemma 3, available in 4B, 12B, and 27B parameter sizes.
Key Highlights:
• Supports 55 languages with high-quality translation across high-, mid-, and low-resource languages
• Exceptional efficiency: 12B model outperforms 27B baseline on WMT24++ benchmark
• Built using two-stage fine-tuning process distilling knowledge from Gemini models
• Retains strong multimodal capabilities (can translate text within images)
• Trained on nearly 500 additional language pairs for research adaptation
• Designed for diverse deployment environments from mobile to cloud
The models achieve state-of-the-art performance while maintaining exceptional efficiency, making high-quality translation accessible across different devices and use cases.
https://huggingface.co/collections/google/translategemma
Google introduces TranslateGemma, a new suite of open translation models based on Gemma 3, available in 4B, 12B, and 27B parameter sizes.
Key Highlights:
• Supports 55 languages with high-quality translation across high-, mid-, and low-resource languages
• Exceptional efficiency: 12B model outperforms 27B baseline on WMT24++ benchmark
• Built using two-stage fine-tuning process distilling knowledge from Gemini models
• Retains strong multimodal capabilities (can translate text within images)
• Trained on nearly 500 additional language pairs for research adaptation
• Designed for diverse deployment environments from mobile to cloud
The models achieve state-of-the-art performance while maintaining exceptional efficiency, making high-quality translation accessible across different devices and use cases.
https://huggingface.co/collections/google/translategemma
takarajordan
posted an update 3 months ago
Post
205
At takara I'm constantly reading papers, I wonder if anyone can train a model to predict popular papers on our dataset?
takara-ai/daily-papers-popularity
takara-ai/daily-papers-popularity
- 1 reply
Post
2736
Genuine recommendation: You should really use this AutoHotKey macro. Save the file as
In my experience the past few months,
macros.ahk and run it. Before sending a prompt to your coding agent, press Ctrl + Alt + 1 and paste your prompt to any regular chatbot. Then send the output to the agent. This is the actual, boring, real way to "10x your prompting". Use the other number keys to avoid repeating yourself over and over again. I use this macro prolly 100-200 times per day. AutoHotKey isn't as new or hype as a lot of other workflows, but there's a reason it's still widely used after 17 years. Don't overcomplicate it.; Requires AutoHotkey v1.1+
; All macros are `Ctrl + Alt + <variable>`
^!1::
Send, Please help me more clearly articulate what I mean with this message (write the message in a code block):
return
^!2::
Send, Please make the following changes:
return
^!3::
Send, It seems you got cut off by the maximum response limit. Please continue by picking up where you left off.
returnIn my experience the past few months,
Ctrl + Alt + 1 works best with Instruct models (non-thinking). Reasoning causes some models to ramble and miss the point. I've just been using GPT-5.x for this. Post
3228
Happy New Year 2026
i have planned to build many things this year , most of them will be cheaper or free alternative's to paid products
i am looking forward to release some useful spaces ✌️ Stay Tuned !
i have planned to build many things this year , most of them will be cheaper or free alternative's to paid products
i am looking forward to release some useful spaces ✌️ Stay Tuned !