🎚️ Batch Normalization — Quand ton réseau a besoin de chill pills ! 😤➡️😌
By
•
•
2🎚️ Batch Normalization — When your neural network needs anger management! 😤➡️😌
By
•
•
2Australian-made LLM beats OpenAI and Google at legal retrieval
By
and 2 others
•
•
25Nemotron’s Open Secret: Accelerating AI Development with Open Models, Data, and Recipes
By
and 1 other
•
•
8Promoter-GPT: Writing DNA Instructions with Language Models
By
•
•
22TIL: How a Harmless Refactor Exposed a Hidden CUDA Bug in Vision-Language Models
By
•
Vision Tokens vs Text Tokens: Understanding the 10× Compression
By
•
•
6Agentic CLIs Can Do So Much More Than Code-Gen
By
•
The Missing Semester of AI for Organizations #2: Risk of Pickle
By
•
•
1Model Card of Xylaria 2 Exempted
By
•
•
2Llama‑Embed‑Nemotron‑8B Text Embedding Model Ranks First on Multilingual MTEB Leaderboard
By
and 4 others
•
•
13🔄 Transfer Learning — Quand l'IA apprend de l'expérience comme toi ! 🎓🚀
By
•
•
2🔄 Transfer Learning — When AI learns from experience like you! 🎓🚀
By
•
•
2Meta-learning Meets Small Models
By
•
•
1Companion AI After the Panic: It’s Okay to Treat Adults Like Adults
By
•
•
4Scaling Test-Time Compute to Achieve Gold Medal at IOI 2025 with Open-Weight Models
By
and 3 others
•
•
17Art of Focus: Page-Aware Sparse Attention and Ling 2.0’s Quest for Efficient Context Length Scaling
By
and 19 others
•
•
14Introducing MTEB v2: Evaluation of embedding and retrieval systems for more than just text
By
and 2 others
•
•
33GSMA Open-Telco LLM Benchmarks 2.0: The first dedicated LLM Evaluation for Telecoms
By
and 15 others
•
•
16How I Built Lightning-Fast Vector Search for Legal Documents
By
•
•
14