bottlecapai/ThinkingCap-Qwen3.6-27B and quants! 50% less thinking tokens on average, and over 90% less in best cases. Achieved via finetuning Qwen3.6-27B (Qwen Team, 2026) with state-of-the-art finetuning algorithms on a curated set of domains with different difficulty. I love fp8 quant 😁

Still listening to radio stations? Someone? I still have a station I like to listen -- Radio Beat [1] . I just want it in an app. So the stream plays nicely with the car navigation. No adds, with playback. I crave nostalgia without the negatives 🤣 [1] www.radiobeat.cz/cs/71/on-lin...

LLMs as Span Annotators: A Comparative Study of LLMs and Humans by @zdenekkasner.cz, @zouharvi.bsky.social, @patuchen.bsky.social, @ivankartac.bsky.social, K. Onderková, @oplatek.bsky.social, Dimitra Gkatzia, @saad.me.uk , @tuetschek.bsky.social & Simone Ballocu aclanthology.org/2026.mme-mai...

New preprint: arxiv.org/abs/2603.20133 Does performance on reasoning benchmarks transfer to real-world settings such as task-oriented dialogue? Not necessarily: our new benchmark tests LLMs on problems framed in both standalone and dialogue settings, and shows that dialogue makes reasoning harder.

Interesting did not know that arxiv requires peer-reviewed papers arxiv.org/abs/2601.17036

Yanai Elazar@yanai.bsky.social · 6mo ago

🚨 New Study 🚨 @arxiv.bsky.social has recently decided to prohibit any 'position' paper from being submitted to its CS servers. Why? Because of the "AI slop", and allegedly higher ratios of LLM-generated content in review papers, compared to non-review papers.

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?...

BottleCapAI Announcement, Seed Round, Pulse: Community News

YouTube video by BottleCapAI

youtu.be

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

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

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...

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

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

👀 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/...

The right words at the right time with the right style for the venue. Proud of our president 🇨🇿 youtu.be/d3wT84egi-g?...

Czech President Delivers Powerful Speech at UN, Slams Russia, Iran, Israel Aggression | AC1G

YouTube video by DRM News

youtu.be

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/...

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

📣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😏

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...

Algorithmic Simplicity

This is an educational channel for all things algorithmic, including but not limited to computer science, machine learning, physics, and mathematics.

youtube.com

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

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

Large Language Models as Span Annotators

Website for the paper Large Language Models as Span Annotators

llm-span-annotators.github.io

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...).

Čech povede evropský výzkum AI - 3. února 05:59 - Studio 6 | Česká televize

Jan Hajič

ceskatelevize.cz

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

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.

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.

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