Adding a GPU Without Building One
FINAL-Bench
• • 17Community Blog & Articles
NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Adding a GPU Without Building One
FINAL-Bench
• • 17Quantum Cryptanalysis on Real Hardware: Pushing Symmetric-Structure Key Recovery Beyond the Published Frontier
FINAL-Bench
• • 15After the party comes the free lunch: regularizing ColBERT models to enhance pooling capabilities and reduce index footprint
lightonai
• • 12Code a simple RAG from scratch
ngxson
• • 359KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 363NVIDIA Isaac Teleop and GR00T 1.7 Open VLA Model Available in LeRobot
nvidia
• • 6Atom2.7m: Representation-Level Specialization for Arithmetic-Aware Small Language Models
ucr-max
• • 6Distillation in 2026 (so far): which frontier models use it and how
sergiopaniego
• • 6Mastering Tensor Dimensions in Transformers
not-lain
• • 19080TB+ of astronomy for the HDD-poor: crossmatch the Multimodal Universe from your laptop
hugging-science
• • 22Does Your LLM Know *When It's About to Be Wrong*?
ginigen-ai
• • 21Meet Cohere Transcribe Arabic
CohereLabs
• • 5Teaching a coding agent to deploy production endpoints on Amazon SageMaker
hf-dwarez
• • 5Agentic RL: Token-In, Token-Out Done Right
huggingface
• • 20Where Does the Signal Live? <br> A Web Data Recipe for Medical Encoder Pretraining
bofenghuang
• • 9Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face
dvgodoy
• • 128A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 36Taking Alpamayo to New Heights with Driving Foundation Models and Closed-Loop Training
nvidia
• • 21🔁 Teaching a 15M French LLM to think deeper — and to know when to stop 🇫🇷
RDTvlokip
• • 3🔁 Apprendre à un LLM français de 15M à penser plus profond — et à savoir quand s'arrêter 🇫🇷
RDTvlokip
• • 3