Daniel Varab

209 posts

Daniel Varab

Daniel Varab

@DanielVarab

LLMs n stuff

Copenhagen, Denmark شامل ہوئے Mayıs 2009
534 فالونگ256 فالوورز
Daniel Varab
Daniel Varab@DanielVarab·
@Teknium I see, so really the all inclusive llm experience. My equivalent is scattered across seasons in CC and desktop Claude I suppose. Awesome. I’ll jump into discord!
English
1
0
2
165
Teknium (e/λ)
Teknium (e/λ)@Teknium·
@DanielVarab Come see our hackathon submissions in our discord there's over 200 use cases there - super creative ones I use hermes-agent to dev hermes agent primarily, and also to manage my minecraft server and do deepresearch and a lot of odds and ends!
English
1
0
7
503
Teknium (e/λ)
Teknium (e/λ)@Teknium·
Alright, the big Question: Which OS do you run Hermes Agent on?
English
49
5
71
9.3K
Daniel Varab ری ٹویٹ کیا
eaclmeeting
eaclmeeting@eaclmeeting·
Reminder: EACL 2026 submissions (via ACL Rolling Review) are due today, October 6, AoE! Do not forget to leave enough time for filling in the responsible NLP checklist! :) Submission link: openreview.net/group?id=aclwe…
eaclmeeting tweet media
English
0
3
13
1.2K
Daniel Varab ری ٹویٹ کیا
CIS, LMU Munich
CIS, LMU Munich@CisLmu·
The CIS institute at LMU Munich has an opening for a tenure-track Akademische/r Rat/Rätin (roughly equivalent to lecturer or junior professor) in NLP / Computational Linguistics. Details are available here: cis.lmu.de/web/arposition…
English
0
9
11
1.8K
Daniel Varab ری ٹویٹ کیا
ACL 2026
ACL 2026@aclmeeting·
🕊️ Lifetime Achievement Award at #ACL2025NLP A standing ovation for Prof. Kathy McKeown, recipient of the ACL 2025 Lifetime Achievement Award! 🌟
English
1
17
122
26.1K
ACL 2026
ACL 2026@aclmeeting·
📚Tom Sherborne: Modeling Cross-lingual Transfer for Semantic Parsing Sherborne’s dissertation developsmethods for cross-lingual transfer into low-resource languages, demonstrating their effectiveness in the context of semantic parsing for integration with database APIs.
English
2
6
43
9.1K
ACL 2026
ACL 2026@aclmeeting·
Selecting the winner among a stellar set of submissions was hard – so the board presents three additional, outstanding theses deserving a honorable mention:
English
2
0
33
5.1K
Daniel Varab ری ٹویٹ کیا
Simon Willison
Simon Willison@simonw·
Workaccount2 on Hacker News just coined the term "context rot" to describe the thing where the quality of an LLM conversation drops as the context fills up with accumulated distractions and dead ends #44310054" target="_blank" rel="nofollow noopener">news.ycombinator.com/item?id=443087…
Simon Willison tweet media
English
112
212
2.7K
282.8K
Daniel Varab ری ٹویٹ کیا
ACL 2026
ACL 2026@aclmeeting·
📢 #ACL2025NLP Dear community! The reviewing deadline for ACL 2025 is approaching -- 23 March! We received over 8000 submissions, the highest number in ACL history. It is particularly important that you submit your reviews on time. A big thank you in advance for all your efforts!
English
1
16
53
9.7K
Daniel Varab ری ٹویٹ کیا
Qwen
Qwen@Alibaba_Qwen·
Today, we release QwQ-32B, our new reasoning model with only 32 billion parameters that rivals cutting-edge reasoning model, e.g., DeepSeek-R1. Blog: qwenlm.github.io/blog/qwq-32b HF: huggingface.co/Qwen/QwQ-32B ModelScope: modelscope.cn/models/Qwen/Qw… Demo: huggingface.co/spaces/Qwen/Qw… Qwen Chat: chat.qwen.ai This time, we investigate recipes for scaling RL and have achieved some impressive results based on our Qwen2.5-32B. We find that RL training con continuously improve the performance especially in math and coding, and we observe that the continous scaling of RL can help a medium-size model achieve competitieve performance against gigantic MoE model. Feel free to chat with our new models and provide us feedback!
Qwen tweet media
English
474
1.5K
8.8K
3.6M
Daniel Varab ری ٹویٹ کیا
Andre Martins
Andre Martins@andre_t_martins·
Good to see @EU_Commission promoting OS LLMs in Europe. However (1) "OpenEuroLLM" is appropriating a name (#EuroLLM) which already exists, (2) it is certainly *not* the "first family of open-source LLMs covering all EU languages" 🧵
European Commission@EU_Commission

AI made in 🇪🇺 OpenEuroLLM, the first family of open source Large Language Models covering all EU languages, has earned the first STEP Seal for its excellence. It brings together EU startups, research labs and supercomputing hosts to train AI on European supercomputers ↓

English
2
13
47
3.9K
Daniel Varab ری ٹویٹ کیا
Victor M
Victor M@victormustar·
Wow I completely missed that: Native VLLM support for Apple Silicon 🔥
Victor M tweet media
English
3
1
13
1.2K
Daniel Varab ری ٹویٹ کیا
Sara Hooker
Sara Hooker@sarahookr·
Excited to share we are hiring for a new type of scholar role. Algorithm interface scholars will re-imagine how humans interact with algorithms. These scholars will lead the frontier in UI-algorithm co-design. 🔥 Join us at @CohereForAI @coherejobs.ashbyhq.com/cohere/dc7da5f…
English
17
43
247
48.8K
Daniel Varab
Daniel Varab@DanielVarab·
@yoavgo @PMinervini Might want to check out the Arc browser. It’s worked wonders for me. Organising tabs, renaming, “projects”,…
English
0
0
1
417
(((ل()(ل() 'yoav))))👾
i was annoyed at having many chrome tabs with PDF papers having uninformative titles, so i created a small chrome extension to fix it. i'm using it for a while now, works well. today i put it on github. enjoy. github.com/yoavg/pdf-tab-…
(((ل()(ل() 'yoav))))👾 tweet media
English
23
64
873
44K
Daniel Varab
Daniel Varab@DanielVarab·
Hi all! I'm looking for backup reviewers for the LM track @ACL2025 (March 18–26). You’ll be exempted from the main review round and thus likely have a reduced workload. Help the community while evaluating fresh-baked LLM research!🍞 Reach out if interested. 🙌 #ACL2025 #NLProc
English
0
0
5
176
Daniel Varab
Daniel Varab@DanielVarab·
@tomhosking Awesome! Never got around to this. Good to see it out :) - Look forward to the read. Hope all is well
English
0
0
0
43
Daniel Varab
Daniel Varab@DanielVarab·
@dnnslmr Fantastisch!! 🔥🔥🔥🔥 Kæmpe tillykke! What a beautiful group of people
Dansk
1
0
1
89