Ondra Platek
@oplatek.bsky.social
PhD candidate@UFAL, Prague. LLM & TTS evaluation. Engineer. Researcher. Speaker. Father.
Interesting did not know that arxiv requires peer-reviewed papers
arxiv.org/abs/2601.17036
arxiv.org/abs/2601.17036
January 29, 2026 at 5:56 PM
Interesting did not know that arxiv requires peer-reviewed papers
arxiv.org/abs/2601.17036
arxiv.org/abs/2601.17036
Our Pulse News App -- our first app is live on iOS today.
We also announce star investors cap.
See the announcement video to see our plans.
If you are LLM guru at research or product building, join us to make the plans a reality
youtu.be/cA8-XJeoZAQ?...
We also announce star investors cap.
See the announcement video to see our plans.
If you are LLM guru at research or product building, join us to make the plans a reality
youtu.be/cA8-XJeoZAQ?...
BottleCapAI Announcement, Seed Round, Pulse: Community News
YouTube video by BottleCapAI
youtu.be
January 29, 2026 at 4:41 PM
Our Pulse News App -- our first app is live on iOS today.
We also announce star investors cap.
See the announcement video to see our plans.
If you are LLM guru at research or product building, join us to make the plans a reality
youtu.be/cA8-XJeoZAQ?...
We also announce star investors cap.
See the announcement video to see our plans.
If you are LLM guru at research or product building, join us to make the plans a reality
youtu.be/cA8-XJeoZAQ?...
Well done @zdenekkasner.bsky.social et al!
LLMs as Span Annotators: A Comparative Study of LLMs and Humans is accepted to multilingual-multicultural-evaluation.github.io 🎉
See paper arxiv.org/abs/2504.08697
LLMs as Span Annotators: A Comparative Study of LLMs and Humans is accepted to multilingual-multicultural-evaluation.github.io 🎉
See paper arxiv.org/abs/2504.08697
January 29, 2026 at 3:35 PM
Well done @zdenekkasner.bsky.social et al!
LLMs as Span Annotators: A Comparative Study of LLMs and Humans is accepted to multilingual-multicultural-evaluation.github.io 🎉
See paper arxiv.org/abs/2504.08697
LLMs as Span Annotators: A Comparative Study of LLMs and Humans is accepted to multilingual-multicultural-evaluation.github.io 🎉
See paper arxiv.org/abs/2504.08697
Dr.LLM: Adaptive Layer Routing for Efficient Inference
Avoiding computation is pretty obvious way how to be more efficient.
The question is how to maintain quality. MoE and router is an efficient approach but suffer from exposure bias fixed thresholds.
arxiv.org/abs/2510.12773
Avoiding computation is pretty obvious way how to be more efficient.
The question is how to maintain quality. MoE and router is an efficient approach but suffer from exposure bias fixed thresholds.
arxiv.org/abs/2510.12773
January 29, 2026 at 3:25 PM
Dr.LLM: Adaptive Layer Routing for Efficient Inference
Avoiding computation is pretty obvious way how to be more efficient.
The question is how to maintain quality. MoE and router is an efficient approach but suffer from exposure bias fixed thresholds.
arxiv.org/abs/2510.12773
Avoiding computation is pretty obvious way how to be more efficient.
The question is how to maintain quality. MoE and router is an efficient approach but suffer from exposure bias fixed thresholds.
arxiv.org/abs/2510.12773
Qwen3 Embedder is amazing
but it is tricky to use.
Left padding confused lot of early adopters.
However, clearly it is the future. Reuse of pre-trained LLM for everything.
Including vector search where BERT-like models ruled.
1/N
arxiv.org/abs/2506.05176
huggingface.co/Qwen/Qwen3-E...
but it is tricky to use.
Left padding confused lot of early adopters.
However, clearly it is the future. Reuse of pre-trained LLM for everything.
Including vector search where BERT-like models ruled.
1/N
arxiv.org/abs/2506.05176
huggingface.co/Qwen/Qwen3-E...
January 29, 2026 at 12:18 PM
Qwen3 Embedder is amazing
but it is tricky to use.
Left padding confused lot of early adopters.
However, clearly it is the future. Reuse of pre-trained LLM for everything.
Including vector search where BERT-like models ruled.
1/N
arxiv.org/abs/2506.05176
huggingface.co/Qwen/Qwen3-E...
but it is tricky to use.
Left padding confused lot of early adopters.
However, clearly it is the future. Reuse of pre-trained LLM for everything.
Including vector search where BERT-like models ruled.
1/N
arxiv.org/abs/2506.05176
huggingface.co/Qwen/Qwen3-E...
The no free lunch idea is here again.
Saw it in TTS models where Guided Attention worked very well. Idea is simple: For speech conversion prefer guide the attention to focus on narrow context. It learns faster.
Looking forward to deep dive on this one - expect similarities
arxiv.org/abs/2601.15165
Saw it in TTS models where Guided Attention worked very well. Idea is simple: For speech conversion prefer guide the attention to focus on narrow context. It learns faster.
Looking forward to deep dive on this one - expect similarities
arxiv.org/abs/2601.15165
The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders. Intuitively, this flexibility implies a solution sp...
arxiv.org
January 29, 2026 at 12:11 PM
The no free lunch idea is here again.
Saw it in TTS models where Guided Attention worked very well. Idea is simple: For speech conversion prefer guide the attention to focus on narrow context. It learns faster.
Looking forward to deep dive on this one - expect similarities
arxiv.org/abs/2601.15165
Saw it in TTS models where Guided Attention worked very well. Idea is simple: For speech conversion prefer guide the attention to focus on narrow context. It learns faster.
Looking forward to deep dive on this one - expect similarities
arxiv.org/abs/2601.15165
👀 WE ARE LOOKING FOR YOU! (yes, you!)
🚨NoCap test deadline 11/11/2025
🏆 $3K / $2K / $1K prizes
Our new team members shared tips&tricks which helped them to go through our test!
TRY IT NOW! 👉 github.com/BottleCapAI/...
🚨NoCap test deadline 11/11/2025
🏆 $3K / $2K / $1K prizes
Our new team members shared tips&tricks which helped them to go through our test!
TRY IT NOW! 👉 github.com/BottleCapAI/...
LinkedIn
This link will take you to a page that’s not on LinkedIn
lnkd.in
November 7, 2025 at 9:54 PM
👀 WE ARE LOOKING FOR YOU! (yes, you!)
🚨NoCap test deadline 11/11/2025
🏆 $3K / $2K / $1K prizes
Our new team members shared tips&tricks which helped them to go through our test!
TRY IT NOW! 👉 github.com/BottleCapAI/...
🚨NoCap test deadline 11/11/2025
🏆 $3K / $2K / $1K prizes
Our new team members shared tips&tricks which helped them to go through our test!
TRY IT NOW! 👉 github.com/BottleCapAI/...
The right words at the right time with the right style for the venue. Proud of our president 🇨🇿
youtu.be/d3wT84egi-g?...
youtu.be/d3wT84egi-g?...
Czech President Delivers Powerful Speech at UN, Slams Russia, Iran, Israel Aggression | AC1G
YouTube video by DRM News
youtu.be
September 26, 2025 at 11:12 AM
The right words at the right time with the right style for the venue. Proud of our president 🇨🇿
youtu.be/d3wT84egi-g?...
youtu.be/d3wT84egi-g?...
Official BottleCapAI: we believe AI shouldn’t cost tens of millions to train.
We are now opening challenge for those who want to help with that!
🏆 $3K / $2K / $1K prizes
⏰ Deadline: 11/11/2025
🖥️ 1 GPU. Your ideas.
👉 Join the NoCap Test:
github.com/BottleCapAI/...
We are now opening challenge for those who want to help with that!
🏆 $3K / $2K / $1K prizes
⏰ Deadline: 11/11/2025
🖥️ 1 GPU. Your ideas.
👉 Join the NoCap Test:
github.com/BottleCapAI/...
GitHub - BottleCapAI/NoCap-Test: Open Test for BottleCapAI
Open Test for BottleCapAI. Contribute to BottleCapAI/NoCap-Test development by creating an account on GitHub.
github.com
September 22, 2025 at 1:41 PM
Official BottleCapAI: we believe AI shouldn’t cost tens of millions to train.
We are now opening challenge for those who want to help with that!
🏆 $3K / $2K / $1K prizes
⏰ Deadline: 11/11/2025
🖥️ 1 GPU. Your ideas.
👉 Join the NoCap Test:
github.com/BottleCapAI/...
We are now opening challenge for those who want to help with that!
🏆 $3K / $2K / $1K prizes
⏰ Deadline: 11/11/2025
🖥️ 1 GPU. Your ideas.
👉 Join the NoCap Test:
github.com/BottleCapAI/...
Reposted by Ondra Platek
📣Take part in 3rd Terminology shared task @WMT!📣
This year:
👉5 language pairs: EN->{ES, RU, DE, ZH},
👉2 tracks - sentence-level and doc-level translation,
👉authentic data from 2 domains: finance and IT!
www2.statmt.org/wmt25/termin...
Don't miss an opportunity - we only do it once in two years😏
This year:
👉5 language pairs: EN->{ES, RU, DE, ZH},
👉2 tracks - sentence-level and doc-level translation,
👉authentic data from 2 domains: finance and IT!
www2.statmt.org/wmt25/termin...
Don't miss an opportunity - we only do it once in two years😏
Terminology Translation Task
www2.statmt.org
June 6, 2025 at 3:54 PM
📣Take part in 3rd Terminology shared task @WMT!📣
This year:
👉5 language pairs: EN->{ES, RU, DE, ZH},
👉2 tracks - sentence-level and doc-level translation,
👉authentic data from 2 domains: finance and IT!
www2.statmt.org/wmt25/termin...
Don't miss an opportunity - we only do it once in two years😏
This year:
👉5 language pairs: EN->{ES, RU, DE, ZH},
👉2 tracks - sentence-level and doc-level translation,
👉authentic data from 2 domains: finance and IT!
www2.statmt.org/wmt25/termin...
Don't miss an opportunity - we only do it once in two years😏
I just found awesome channel on YouTube.
It has 77k subscribers with just 7 videos.
Because the videos are just awesome!
I wish I could explain stuff that simply!
Does anybody know how long take to prepare such video?
www.youtube.com/@algorithmic...
It has 77k subscribers with just 7 videos.
Because the videos are just awesome!
I wish I could explain stuff that simply!
Does anybody know how long take to prepare such video?
www.youtube.com/@algorithmic...
Algorithmic Simplicity
This is an educational channel for all things algorithmic, including but not limited to computer science, machine learning, physics, and mathematics.
www.youtube.com
May 4, 2025 at 9:00 AM
I just found awesome channel on YouTube.
It has 77k subscribers with just 7 videos.
Because the videos are just awesome!
I wish I could explain stuff that simply!
Does anybody know how long take to prepare such video?
www.youtube.com/@algorithmic...
It has 77k subscribers with just 7 videos.
Because the videos are just awesome!
I wish I could explain stuff that simply!
Does anybody know how long take to prepare such video?
www.youtube.com/@algorithmic...
Reposted by Ondra Platek
Thanks to all my awesome collaborators!
👉️ Vilém @zouharvi.bsky.social
👉️ Patrícia @patuchen.bsky.social
👉️ Ivan @ivankartac.bsky.social
👉️ Kristýna Onderková
👉️ Ondřej P. @oplatek.bsky.social
👉️ Dimitra @dimitrag.bsky.social
👉️ Saad @saad.me.uk
👉️ Ondřej D. @tuetschek.bsky.social
👉️ Simone Balloccu
👉️ Vilém @zouharvi.bsky.social
👉️ Patrícia @patuchen.bsky.social
👉️ Ivan @ivankartac.bsky.social
👉️ Kristýna Onderková
👉️ Ondřej P. @oplatek.bsky.social
👉️ Dimitra @dimitrag.bsky.social
👉️ Saad @saad.me.uk
👉️ Ondřej D. @tuetschek.bsky.social
👉️ Simone Balloccu
April 15, 2025 at 11:10 AM
Thanks to all my awesome collaborators!
👉️ Vilém @zouharvi.bsky.social
👉️ Patrícia @patuchen.bsky.social
👉️ Ivan @ivankartac.bsky.social
👉️ Kristýna Onderková
👉️ Ondřej P. @oplatek.bsky.social
👉️ Dimitra @dimitrag.bsky.social
👉️ Saad @saad.me.uk
👉️ Ondřej D. @tuetschek.bsky.social
👉️ Simone Balloccu
👉️ Vilém @zouharvi.bsky.social
👉️ Patrícia @patuchen.bsky.social
👉️ Ivan @ivankartac.bsky.social
👉️ Kristýna Onderková
👉️ Ondřej P. @oplatek.bsky.social
👉️ Dimitra @dimitrag.bsky.social
👉️ Saad @saad.me.uk
👉️ Ondřej D. @tuetschek.bsky.social
👉️ Simone Balloccu
Reposted by Ondra Platek
How do LLMs compare to human crowdworkers in annotating text spans? 🧑🤖
And how can span annotation help us with evaluating texts?
Find out in our new paper: llm-span-annotators.github.io
Arxiv: arxiv.org/abs/2504.08697
And how can span annotation help us with evaluating texts?
Find out in our new paper: llm-span-annotators.github.io
Arxiv: arxiv.org/abs/2504.08697
Large Language Models as Span Annotators
Website for the paper Large Language Models as Span Annotators
llm-span-annotators.github.io
April 15, 2025 at 11:10 AM
How do LLMs compare to human crowdworkers in annotating text spans? 🧑🤖
And how can span annotation help us with evaluating texts?
Find out in our new paper: llm-span-annotators.github.io
Arxiv: arxiv.org/abs/2504.08697
And how can span annotation help us with evaluating texts?
Find out in our new paper: llm-span-annotators.github.io
Arxiv: arxiv.org/abs/2504.08697
Reposted by Ondra Platek
We've been making the media rounds!
👉📺 @hajicjan.bsky.social talked about the new OpenEuroLLM project on Czech TV's Studio 6 www.ceskatelevize.cz/porady/10969...
👉📻 @tuetschek.bsky.social discussed #LLMs on Czech Radio radiozurnal.rozhlas.cz/proc-umela-i...).
👉📺 @hajicjan.bsky.social talked about the new OpenEuroLLM project on Czech TV's Studio 6 www.ceskatelevize.cz/porady/10969...
👉📻 @tuetschek.bsky.social discussed #LLMs on Czech Radio radiozurnal.rozhlas.cz/proc-umela-i...).
Čech povede evropský výzkum AI - 3. února 05:59 - Studio 6 | Česká televize
Jan Hajič
www.ceskatelevize.cz
February 7, 2025 at 9:44 PM
We've been making the media rounds!
👉📺 @hajicjan.bsky.social talked about the new OpenEuroLLM project on Czech TV's Studio 6 www.ceskatelevize.cz/porady/10969...
👉📻 @tuetschek.bsky.social discussed #LLMs on Czech Radio radiozurnal.rozhlas.cz/proc-umela-i...).
👉📺 @hajicjan.bsky.social talked about the new OpenEuroLLM project on Czech TV's Studio 6 www.ceskatelevize.cz/porady/10969...
👉📻 @tuetschek.bsky.social discussed #LLMs on Czech Radio radiozurnal.rozhlas.cz/proc-umela-i...).
Reposted by Ondra Platek
Congrats to ✨Šárka Zikánová✨on her promotion to Associate Professor! 🎉 Her research explores syntax, information structure, and discourse relations in Czech and beyond. She contributed to key linguistic corpora and now focuses on psycholinguistic studies of discourse. ufal.mff.cuni.cz/sarka-zikanova
Šárka Zikánová | ÚFAL
ufal.mff.cuni.cz
February 25, 2025 at 10:44 AM
Congrats to ✨Šárka Zikánová✨on her promotion to Associate Professor! 🎉 Her research explores syntax, information structure, and discourse relations in Czech and beyond. She contributed to key linguistic corpora and now focuses on psycholinguistic studies of discourse. ufal.mff.cuni.cz/sarka-zikanova
Reposted by Ondra Platek
Hello Blue Sky! 👋 This is the official account of the Institute of Formal and Applied Linguistics (ÚFAL for short) at the Faculty of Mathematics and Physics, Charles University in Prague 🇨🇿. Here, we will share news from the life of the institute and our members.
November 19, 2024 at 7:09 PM
Hello Blue Sky! 👋 This is the official account of the Institute of Formal and Applied Linguistics (ÚFAL for short) at the Faculty of Mathematics and Physics, Charles University in Prague 🇨🇿. Here, we will share news from the life of the institute and our members.
Reposted by Ondra Platek
Today is the Open Doors Day🚪at Matfzy, Charles University. @rur.bsky.social and @zdenekkasner.bsky.social chat with high schoolers about #LLMs and #LanguageTechnology... @rudolf_rosa shows a demo of automatic interpreting 🗣️🎙️🌐 by Dominik Macháček and Ondřej Bojar.
November 28, 2024 at 12:42 PM
Today is the Open Doors Day🚪at Matfzy, Charles University. @rur.bsky.social and @zdenekkasner.bsky.social chat with high schoolers about #LLMs and #LanguageTechnology... @rudolf_rosa shows a demo of automatic interpreting 🗣️🎙️🌐 by Dominik Macháček and Ondřej Bojar.
Hello Bsky!
Let me introduce github.com/ufal/factgenie
A Span Annotation tool from @ufal-cuni.bsky.social
💡 Annotate errors in the outputs & w/out any references
💪 Use many ready-to-use datasets for data-to-text. MT & NLP friends are coming...
🚀 You get your annotations in minutes.
Let me introduce github.com/ufal/factgenie
A Span Annotation tool from @ufal-cuni.bsky.social
💡 Annotate errors in the outputs & w/out any references
💪 Use many ready-to-use datasets for data-to-text. MT & NLP friends are coming...
🚀 You get your annotations in minutes.
November 20, 2024 at 7:12 AM
Hello Bsky!
Let me introduce github.com/ufal/factgenie
A Span Annotation tool from @ufal-cuni.bsky.social
💡 Annotate errors in the outputs & w/out any references
💪 Use many ready-to-use datasets for data-to-text. MT & NLP friends are coming...
🚀 You get your annotations in minutes.
Let me introduce github.com/ufal/factgenie
A Span Annotation tool from @ufal-cuni.bsky.social
💡 Annotate errors in the outputs & w/out any references
💪 Use many ready-to-use datasets for data-to-text. MT & NLP friends are coming...
🚀 You get your annotations in minutes.
Reposted by Ondra Platek
When a model output gets a BLEU score of 12.34: 😶
When you can *see* the errors in the output: 🤯
Check out factgenie, our new error span annotation tool:
github.com/ufal/factgenie
(Just matured into v1.0.1! 🎂)
#nlp #nlg
When you can *see* the errors in the output: 🤯
Check out factgenie, our new error span annotation tool:
github.com/ufal/factgenie
(Just matured into v1.0.1! 🎂)
#nlp #nlg
November 14, 2024 at 1:37 PM
When a model output gets a BLEU score of 12.34: 😶
When you can *see* the errors in the output: 🤯
Check out factgenie, our new error span annotation tool:
github.com/ufal/factgenie
(Just matured into v1.0.1! 🎂)
#nlp #nlg
When you can *see* the errors in the output: 🤯
Check out factgenie, our new error span annotation tool:
github.com/ufal/factgenie
(Just matured into v1.0.1! 🎂)
#nlp #nlg