NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
Scaling OpenEnv: From Free Usage to Thousands of Concurrent Environments
One Year Since the “DeepSeek Moment”
•
6
🪄 Interpreto: A Unified Toolkit for Interpretability of Transformer Models
•
10
Running Claude Code with Local Models via Ollama (NVIDIA's nemotron-3-nano)
🧠🌍 Training Open-Source AI for the Zomi Language
A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family
•
27
New in llama.cpp: Anthropic Messages API
•
23
Edge vs Cloud GPUs for Inference: When to Run Models Locally and When to Use a GPU Cloud
Latency vs Throughput: Why Both Matter in Enterprise Cloud Deployments
LoongFlow: An Open-Sourced Agent Framework That Transforms Expert Experience into Autonomous AI Productivity
•
1
Python Doesn't Need To Be Slow: From 405s to 0.06s with N-Body Simulations 🚀
•
1
MAD GRPO: Treating Dr. GRPO that tried to fix GRPO but brought instability and verbosity bias
ZeroTime-Bot: Medical Triage Alignment with GRPO and Unsloth
🎯 F1-Score — Quand l'Accuracy te ment en pleine face ! 📊💥
•
1
🎯 F1-Score — When Accuracy lies to your face! 📊💥
•
1
The autonomous and interconnected cars revolution
Beyond Brute Force: Why LoongFlow is the “Thinking” Evolution of OpenEvolve
•
4
Introducing OptiMind, a research model designed for optimization
•
23