Post
3316
Two big projects are open sourced soon. Get ready...
- 11 replies
Demian L. P.
very-cooluser
·
AI & ML interests
Anything that can run on ~3GB of memory is a instant thumbs up to me
Recent Activity
upvoted a paper 29 days ago
The Verification Horizon: No Silver Bullet for Coding Agent RewardsOrganizations
None yet
reacted to appvoid's post with 🔥 5 days ago
upvoted 6
papers 29 days ago
Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System
Paper • 2606.18112 • Published • 27
The Verification Horizon: No Silver Bullet for Coding Agent Rewards
Paper • 2606.26300 • Published • 51
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
Paper • 2606.26907 • Published • 49
Native Active Perception as Reasoning for Omni-Modal Understanding
Paper • 2606.19341 • Published • 19
Rethinking the Role of Efficient Attention in Hybrid Architectures
Paper • 2606.15378 • Published • 20
Qwen-Image-2.0-RL Technical Report
Paper • 2606.27608 • Published • 52
upvoted a paper about 1 month ago
Pytorch model
#6 opened about 2 months ago
by very-cooluser
liked a
model 2 months ago
liked a
dataset 2 months ago
liked a
model 2 months ago
upvoted an article 2 months ago
Article
An experiment with attention.
wop
• • 6 upvoted 3
papers 2 months ago
OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization
Paper • 2605.21226 • Published • 9
SAME: A Semantically-Aligned Music Autoencoder
Paper • 2605.18613 • Published • 4
Measuring Maximum Activations in Open Large Language Models
Paper • 2605.15572 • Published • 18
upvoted 2
articles 2 months ago
Article
Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step
FINAL-Bench
• • 18 Article
Vocabulary-Augmented Prompting for Sango — Production African Language AI Without a Parallel Corpus
MEYNG
• • 2 upvoted a paper 3 months ago
reacted to qgallouedec's post with 🔥 3 months ago
Post
10611
Shipped hf-sandbox! 🥡
🧪 Running an eval that executes model-generated C on a few thousand prompts? You probably don't want any of that on your laptop.
Just shipped hf-sandbox, a Modal-style sandbox API on top of Hugging Face Jobs. Spin up an isolated, ephemeral container, run untrusted code, get the result back. No Docker on your laptop, no infra to manage.
Just pip install hf-sandbox.
Early days (v0.1); feedback and issues very welcome:
👉 https://github.com/huggingface/hf-sandbox
🧪 Running an eval that executes model-generated C on a few thousand prompts? You probably don't want any of that on your laptop.
Just shipped hf-sandbox, a Modal-style sandbox API on top of Hugging Face Jobs. Spin up an isolated, ephemeral container, run untrusted code, get the result back. No Docker on your laptop, no infra to manage.
Just pip install hf-sandbox.
Early days (v0.1); feedback and issues very welcome:
👉 https://github.com/huggingface/hf-sandbox
- 1 reply