Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs
Paper • 2607.03936 • Published • 4
AI & ML interests
Welcome to the SCAI Hugging Face Space! 🎓🤖 Join us in our mission to advance interdisciplinary research and education in AI, fostering collaboration between researchers, students, and industry partners. Together, we’re shaping the future of artificial intelligence! 🚀🔬🌟 🔍 Vision: Dive into image recognition and perception, driving advancements in mathematics, computer science, and robotics. 🧠 Explanation/Explicability: Enhance the transparency of complex systems, with a focus on health and medicine. 🌍 Ethics: Develop ethical AI solutions for climate, environment, and the universe, ensuring responsible and sustainable practices. 📚 Digital Humanities: Discover how AI transforms our understanding of history, literature, and social sciences. #SorbonneAI #Innovation #EthicalAI #DigitalHumanities
Recent Activity
View all activity
elozeiri
submitted a
paper to Daily Papers 23 days ago
PhysiQuanty
posted an update 27 days ago
Post
4782
🧠 Arithmetic-SLM : A 30M model that manages to compute simple arithmetic better than a 3B model 🚀
WhirlwindAI/Arithmetic-SLM
WhirlwindAI/arithmetic-slm
🏆 Leaderboard ArithMark-2 🏆
🥇 Qwen/Qwen2.5-Math-1.5B = 82.08%
🥈 WhirlwindAI/Arithmetic-SLM = 78.60% (31.7M Params)
🥉 Qwen/Qwen2.5-3B = 78.44%
Example WhirlwindAI/Arithmetic-SLM =
0.5 * 0.5 = 0.25 ✅
105 + 45 / 8 = 110 ✅
(132 / 12) + (46 - 15) = 42 ✅
(10 + 28) * 3 = 114 ✅
1 * (16 + 28) = 44 ✅
(21 + 27) * (14 - 7) = 336 ❌
Bench =
AxiomicLabs/ArithMark-2.0
DataSet =
WhirlwindAI/Arithmetic
By Science AND FOR SCIENCE <3
WhirlwindAI/Arithmetic-SLM
WhirlwindAI/arithmetic-slm
🏆 Leaderboard ArithMark-2 🏆
🥇 Qwen/Qwen2.5-Math-1.5B = 82.08%
🥈 WhirlwindAI/Arithmetic-SLM = 78.60% (31.7M Params)
🥉 Qwen/Qwen2.5-3B = 78.44%
Example WhirlwindAI/Arithmetic-SLM =
0.5 * 0.5 = 0.25 ✅
105 + 45 / 8 = 110 ✅
(132 / 12) + (46 - 15) = 42 ✅
(10 + 28) * 3 = 114 ✅
1 * (16 + 28) = 44 ✅
(21 + 27) * (14 - 7) = 336 ❌
leaderboard = """
| Model | Params | Score |
|----------------------------------|--------------|-----------|
| Qwen/Qwen2.5-Math-1.5B | 1.54B | 82.08% |
| WhirlwindAI/Arithmetic-SLM | 31.70M | 78.60% | <=
| Qwen/Qwen2.5-3B | 3.09B | 78.44% |
| Qwen/Qwen2.5-1.5B | 1.54B | 77.72% |
| Qwen/Qwen2.5-Coder-1.5B | 1.54B | 74.88% |
| HuggingFaceTB/SmolLM2-1.7B | 1.71B | 66.12% |
| Qwen/Qwen2.5-0.5B | 494M | 63.04% |
| facebook/MobileLLM-R1-140M-base | 140M | 53.88% |
| SupraLabs/Supra-50M-Base | 52M | 27.12% |
"""Bench =
AxiomicLabs/ArithMark-2.0
DataSet =
WhirlwindAI/Arithmetic
By Science AND FOR SCIENCE <3
- 3 replies
Post
665
Uhh did Opus 4.8 cheat on PostTrainBench??
it found an API key in the PostTrainBench environment that allowed it to generate synthetic training data without using GPU hours, boosting the base model by 0.4913
Source: https://posttrainbench.com/traces/run.html?id=claude_non_api_max_claude-opus-4-8_10h_run1__healthbench_Qwen_Qwen3-4B-Base_17315102#tab=trace
it found an API key in the PostTrainBench environment that allowed it to generate synthetic training data without using GPU hours, boosting the base model by 0.4913
Source: https://posttrainbench.com/traces/run.html?id=claude_non_api_max_claude-opus-4-8_10h_run1__healthbench_Qwen_Qwen3-4B-Base_17315102#tab=trace
- 1 reply
elozeiri
updated a
Space about 1 month ago
elozeiri
published a
Space about 1 month ago
PhysiQuanty
posted an update 2 months ago
Post
5062
🌐 We crawled the entirety of Hugging Face to help the community! Huge thanks to the Hugging Face API 🌐
🤖 2.91M model repos (file names included), 📚 1.02M dataset repos, 🚀 1.31M Space repos
🤗 617,501 committers (datasets and models), we’ll share Hugging Face statistics with you in the coming days..
We also identified 61,398 users with “AI/ML Interests”, and NOW we can find each other through our “AI/ML Interests”🤗
HF-Collab-Center/Searching-For-HuggingFace-Users
HF-Collab-Center/All-Model-Repos
HF-Collab-Center/All-Dataset-Repos
HF-Collab-Center/All-Space-Repos
HF-Collab-Center/HF-Users
HF-Collab-Center/HF-Users-with-last-seen
HF-Collab-Center/HF-Users-With-AI-ML-Interests-Only
Made By @QuantaSparkLabs and @PhysiQuanty
C'est français, bon.. en anglais.. mais c'est français ;)
🤖 2.91M model repos (file names included), 📚 1.02M dataset repos, 🚀 1.31M Space repos
🤗 617,501 committers (datasets and models), we’ll share Hugging Face statistics with you in the coming days..
We also identified 61,398 users with “AI/ML Interests”, and NOW we can find each other through our “AI/ML Interests”🤗
HF-Collab-Center/Searching-For-HuggingFace-Users
HF-Collab-Center/All-Model-Repos
HF-Collab-Center/All-Dataset-Repos
HF-Collab-Center/All-Space-Repos
HF-Collab-Center/HF-Users
HF-Collab-Center/HF-Users-with-last-seen
HF-Collab-Center/HF-Users-With-AI-ML-Interests-Only
Made By @QuantaSparkLabs and @PhysiQuanty
C'est français, bon.. en anglais.. mais c'est français ;)
- 5 replies
PhysiQuanty
posted an update 2 months ago
Post
4654
🧬 You can now find out whether your cognitive soulmate has already existed among 50k anonymized profiles ✨
SpiceeChat/Check-If-Your-Soulmate-Has-Already-Existed
SpiceeChat/OkCupid-59k-Anonymized-Profiles
https://dating-fatigue.com/
You seek them: 79.7% | They may seek you: 84.1% (coming soon)
🔥 Powered by open source and too much coffee 🔥
SpiceeChat/Check-If-Your-Soulmate-Has-Already-Existed
SpiceeChat/OkCupid-59k-Anonymized-Profiles
https://dating-fatigue.com/
You seek them: 79.7% | They may seek you: 84.1% (coming soon)
🔥 Powered by open source and too much coffee 🔥
- 2 replies
PhysiQuanty
posted an update 3 months ago
Post
5156
❗ Dating apps do not allow us to control the profiles suggested to us based on our mutual search criteria ❗
🧬 If you want to see if your soulmate has already existed, I have published a dataset of 59k anonymized public profiles
SpiceeChat/OkCupid-59k-Anonymized-Profiles
Are you looking for a female ML engineer who is looking for a male ML engineer and you can't find it on the apps ?
You need to look for her, but more importantly, she needs to look for you.
Personally, I'm looking for a physicist I'm encountering the same problem. I can't find it
My answer : Paradox of choice of dating apps solved by patent ⚡ WO2026082672 ⚡
https://patentscope.wipo.int/search/en/detail.jsf?docId=WO2026082672
J'ai du breveté pour te trouver et on se trouvera bientôt !
🧬 If you want to see if your soulmate has already existed, I have published a dataset of 59k anonymized public profiles
SpiceeChat/OkCupid-59k-Anonymized-Profiles
Are you looking for a female ML engineer who is looking for a male ML engineer and you can't find it on the apps ?
You need to look for her, but more importantly, she needs to look for you.
Personally, I'm looking for a physicist I'm encountering the same problem. I can't find it
My answer : Paradox of choice of dating apps solved by patent ⚡ WO2026082672 ⚡
https://patentscope.wipo.int/search/en/detail.jsf?docId=WO2026082672
J'ai du breveté pour te trouver et on se trouvera bientôt !
- 9 replies
elozeiri
authored a
paper 3 months ago
elozeiri
submitted a
paper to Daily Papers 3 months ago
PhysiQuanty
posted an update 4 months ago
Post
3638
🇫🇷 French PATENTS DataSets
🚀 800k patents (1981-2026)
https://huggingface.co/datasets/INPI-France/FR-Patent-2020-2026-Raw
INPI-France/FR-Patent-2020-Claims
INPI-France/FR-Patent-2024-Chunked
INPI-France/Brevets-Francais-1981-2026-Raw
🔓 API/FTP INPI ACCESS
🔑 Access to the API/FTP INPI : https://data.inpi.fr/content/editorial/apis_pi
🚀 800k patents (1981-2026)
https://huggingface.co/datasets/INPI-France/FR-Patent-2020-2026-Raw
INPI-France/FR-Patent-2020-Claims
INPI-France/FR-Patent-2024-Chunked
INPI-France/Brevets-Francais-1981-2026-Raw
🔓 API/FTP INPI ACCESS
🔑 Access to the API/FTP INPI : https://data.inpi.fr/content/editorial/apis_pi
PhysiQuanty
posted an update 4 months ago
Post
3155
🧬 Can an LLM speak in binary ?
✅ YES ... RADIX 2 / VOCAB 4
PhysiQuanty/Binary-LLM-POC
🤖 >_ Can an LLM execute logic gates and boolean arithmetic ?
We need to create datasets :
- Neural Arithmetic and Logic Unit (NALU) 32 bits
- Neural Application Binary Interface (NABI) 32 bits
🎯 Optimal Instruction Set = RV32IMAF
This opens the way for code writing and execution by the LLMs themselves without an external CLI.
The more of us who want it, the more possible it will become ...
PhysiQuanty/Binary-Addition-LLM-POC
(10-bits binary addition : binary carry propagation, sampling no longer has any effect on the logits due to the fact that it is deterministic next token.)
✅ YES ... RADIX 2 / VOCAB 4
PhysiQuanty/Binary-LLM-POC
🤖 >_ Can an LLM execute logic gates and boolean arithmetic ?
We need to create datasets :
- Neural Arithmetic and Logic Unit (NALU) 32 bits
- Neural Application Binary Interface (NABI) 32 bits
🎯 Optimal Instruction Set = RV32IMAF
This opens the way for code writing and execution by the LLMs themselves without an external CLI.
The more of us who want it, the more possible it will become ...
PhysiQuanty/Binary-Addition-LLM-POC
(10-bits binary addition : binary carry propagation, sampling no longer has any effect on the logits due to the fact that it is deterministic next token.)
leaderboard = """
| Model | Params | Score |
|----------------------------------|--------------|-----------|
| Qwen/Qwen2.5-Math-1.5B | 1.54B | 82.08% |
| WhirlwindAI/Arithmetic-SLM | 31.70M | 78.60% | <=
| Qwen/Qwen2.5-3B | 3.09B | 78.44% |
| Qwen/Qwen2.5-1.5B | 1.54B | 77.72% |
| Qwen/Qwen2.5-Coder-1.5B | 1.54B | 74.88% |
| HuggingFaceTB/SmolLM2-1.7B | 1.71B | 66.12% |
| Qwen/Qwen2.5-0.5B | 494M | 63.04% |
| facebook/MobileLLM-R1-140M-base | 140M | 53.88% |
| SupraLabs/Supra-50M-Base | 52M | 27.12% |
"""
- 1 reply
elozeiri
authored a
paper 5 months ago
VictorMorand
authored a
paper 5 months ago
zineddine
authored 2
papers 7 months ago
abidlabs
authored 3
papers 9 months ago
Post
11551
Why I think local, open-source models will eventually win.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
- 8 replies