Zero-shot World Models Are Developmentally Efficient Learners
Paper โข 2604.10333 โข Published โข 7
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Sparse Reward Subsystem in Large Language Models
Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
awwklย
submitted a
paper to Daily Papers about 1 month ago
Post
3117
The moment we've been waiting for โ ACE-Step dropped their new model: Ace-Step 1.5 ๐
๐ ACE-Step/Ace-Step1.5
And the best part? It's released under the MIT license.
We've already started integrating it into our project. Let's go ๐
๐ ACE-Step/Ace-Step1.5
And the best part? It's released under the MIT license.
We've already started integrating it into our project. Let's go ๐
- 1 reply
Xkevย
submitted a
paper to Daily Papers 3 months ago
Post
1418
๐ฎ Introducing: Paper Popularity Game
Think you know which AI papers go viral? Test your instincts!
I built a little game where you try to guess the popularity of AI research papers from the Hugging Face Daily Papers feed.
How it works:
You'll see two papers side by sideโread the titles, check the abstracts, and pick which one you think got more upvotes from the HF community.
It's a great way to discover trending AI research while having fun.
Tests your intuition about what the ML community finds interesting.
Try it out:
efecelik/paper-popularity-game
Would love to hear your high scores and feedback!
Think you know which AI papers go viral? Test your instincts!
I built a little game where you try to guess the popularity of AI research papers from the Hugging Face Daily Papers feed.
How it works:
You'll see two papers side by sideโread the titles, check the abstracts, and pick which one you think got more upvotes from the HF community.
It's a great way to discover trending AI research while having fun.
Tests your intuition about what the ML community finds interesting.
Try it out:
efecelik/paper-popularity-game
Would love to hear your high scores and feedback!
Post
1642
Interesting paper: PhysRVG
The core idea: instead of treating physics as a soft condition the model can work around during optimization, enforce it strictly via reinforcement learning. The paper focuses on rigid body dynamics - collisions, pendulums, free fall, rolling.
PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models (2601.11087)
The core idea: instead of treating physics as a soft condition the model can work around during optimization, enforce it strictly via reinforcement learning. The paper focuses on rigid body dynamics - collisions, pendulums, free fall, rolling.
PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models (2601.11087)
- 2 replies
Post
639
Having multiple perspectives helps me create more diverse, innovative projects but without deep mastery in one area, I never feel truly satisfied.
What's the better investment: going deep in one field, or staying broad across many?
What's the better investment: going deep in one field, or staying broad across many?
- 2 replies
Post
2537
My First MCP Server: DataView
Browse HuggingFace datasets directly from your AI assistant.
-Search & filter datasets
-View rows & stats
-SQL queries & Parquet export
efecelik/dataview-mcp
Browse HuggingFace datasets directly from your AI assistant.
-Search & filter datasets
-View rows & stats
-SQL queries & Parquet export
efecelik/dataview-mcp
Post
252
We Built a Music App with ACE-Step โ Looking for Feedback
Hey everyone,
We've been building AceSteps โ a platform where anyone can create music using the ACE-Step model ( ACE-Step/ACE-Step-v1-3.5B). You can mint your tracks as NFTs, tokenize them into 100,000 fractional shares, and trade them on Uniswap V4. When your song gets popular, token holders earn from ad revenue automatically. It's a Farcaster Mini-App on Base Network.
But we want to make it better, and we'd love your input:
What's the one feature that would make you actually use an AI music tool regularly?
Andd any suggestions on how we can make this model better? Actually sharing here for this question. ๐ค
Any feedback, ideas, or critiques are welcome.
๐ https://docs.acesteps.com/
๐ https://docs.acesteps.com/pitch-deck.html
๐ https://farcaster.xyz/?launchFrameUrl=https%3A%2F%2Fwww.acesteps.com%2F
๐ https://www.acesteps.com
Hey everyone,
We've been building AceSteps โ a platform where anyone can create music using the ACE-Step model ( ACE-Step/ACE-Step-v1-3.5B). You can mint your tracks as NFTs, tokenize them into 100,000 fractional shares, and trade them on Uniswap V4. When your song gets popular, token holders earn from ad revenue automatically. It's a Farcaster Mini-App on Base Network.
But we want to make it better, and we'd love your input:
What's the one feature that would make you actually use an AI music tool regularly?
Andd any suggestions on how we can make this model better? Actually sharing here for this question. ๐ค
Any feedback, ideas, or critiques are welcome.
๐ https://docs.acesteps.com/
๐ https://docs.acesteps.com/pitch-deck.html
๐ https://farcaster.xyz/?launchFrameUrl=https%3A%2F%2Fwww.acesteps.com%2F
๐ https://www.acesteps.com
Post
2320
why ACE-Step model isn't popular that much? imo it makes really good music.
ACE-Step/ACE-Step-v1-3.5B
ACE-Step/ACE-Step-v1-3.5B
- 2 replies
Post
3638
Muon vs MuonClip vs Muon+Adamw
Muon has gone from an experiment to a mainstream optimizer, but does it hold up for fineโtuning? We ran headโtoโhead tests on Qwen3โ4B (10k+ highโquality instruction rows) to find out.
Short story: Pure Muon converged fastest at the start, but its gradientโnorm spikes made training unstable. MuonClip (Kimi K2โs clipping) stabilizes long pretraining runs, yet in our smallโscale fineโtune it underperformed, lower token accuracy and slower convergence. The winner was the hybrid: Muon for 2D layers + AdamW for 1D layers. It delivered the best balance of stability and final performance and even beat vanilla AdamW.
Takeaway: for small-scale fine-tuning, hybrid = practical and reliable.
Next Step: scale to larger models/datasets to see if Muonโs spikes become catastrophic or if clipping wins out.
Full Blog Link: https://huggingface.co/blog/KingNish/optimizer-part1
Muon has gone from an experiment to a mainstream optimizer, but does it hold up for fineโtuning? We ran headโtoโhead tests on Qwen3โ4B (10k+ highโquality instruction rows) to find out.
Short story: Pure Muon converged fastest at the start, but its gradientโnorm spikes made training unstable. MuonClip (Kimi K2โs clipping) stabilizes long pretraining runs, yet in our smallโscale fineโtune it underperformed, lower token accuracy and slower convergence. The winner was the hybrid: Muon for 2D layers + AdamW for 1D layers. It delivered the best balance of stability and final performance and even beat vanilla AdamW.
Takeaway: for small-scale fine-tuning, hybrid = practical and reliable.
Next Step: scale to larger models/datasets to see if Muonโs spikes become catastrophic or if clipping wins out.
Full Blog Link: https://huggingface.co/blog/KingNish/optimizer-part1
Post
2812
I tested Muon vs MuonClip vs Muon+AdamW for fine-tuning LLMs
Just published a blog on that, Read here ๐ https://huggingface.co/blog/KingNish/optimizer-part1
Just published a blog on that, Read here ๐ https://huggingface.co/blog/KingNish/optimizer-part1
- 1 reply
kzliuย
authored a
paper 9 months ago
Post
2233
Wan 2.2 fast upto 10x faster than original wan 2.2
Model: FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers
Space: KingNish/wan2-2-fast
Model: FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers
Space: KingNish/wan2-2-fast
Post
1229
What's currently the biggest gap in Open Source Datasets ??
- 5 replies
Kameshrย
updated a
dataset about 1 year ago
Kameshrย
published a
dataset about 1 year ago
Post
7983
๐AraClip is now fully integrated with Hugging Face ๐ค
AraClip is a specialized CLIP model that was created by @pain and optimized for Arabic text-image retrieval tasks๐ฅ
๐ Try it out ๐
๐ค model: Arabic-Clip/araclip
๐งฉ Gradio demo: Arabic-Clip/Araclip-Simplified
๐ website: https://arabic-clip.github.io/Arabic-CLIP/
AraClip is a specialized CLIP model that was created by @pain and optimized for Arabic text-image retrieval tasks๐ฅ
๐ Try it out ๐
๐ค model: Arabic-Clip/araclip
๐งฉ Gradio demo: Arabic-Clip/Araclip-Simplified
๐ website: https://arabic-clip.github.io/Arabic-CLIP/
- 2 replies
Post
4594
I have just released a new blogpost about kv caching and its role in inference speedup ๐
๐ https://huggingface.co/blog/not-lain/kv-caching/
some takeaways :
๐ https://huggingface.co/blog/not-lain/kv-caching/
some takeaways :
- 4 replies
Post
1840
we now have more than 2000 public AI models using ModelHubMixin๐ค
Post
4183
Published a new blogpost ๐
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
๐ https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
๐ https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :