Community Blog & Articles
NEW Articles from Team or Enterprise organizations will get promoted to the main section. Building Moon Bot: A Slack-Native Coding Agent Backed by HuggingFace Buckets
huggingface
• • 38
Kog Laneformer 2B: The Latency-First Model Behind Kog Inference Engine
VLX-Flow: Continuous Video Understanding for Real-Time Multimodal Interaction
VLX-Seek: Improving VLM Fine-Grained Perception via Region Reference Instead of Coordinate Generation
How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent
nvidia
• • 66
Introducing North Mini Code: Cohere’s First Model For Developers
CohereLabs
• • 77
Interhuman’s Goblin: “Yeah, Friday at Five”
Interhuman
• • 6
VLX-Go: Vision-Language Short-Horizon Waypoint Prediction for Embodied Navigation
omlab
• • 6
Where Does the Signal Live? <br> A Web Data Recipe for Medical Encoder Pretraining
bofenghuang
• • 5
V-Zero
Introduction to State Space Models (SSM)
lbourdois
• • 232
Uncensor any LLM with abliteration
mlabonne
• • 868
A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 33
Continuous batching for GRPO, now in TRL
sergiopaniego
• • 7
Code a simple RAG from scratch
ngxson
• • 351
Diffusion Language Models: The New Paradigm
ProCreations
• • 51
Party is over: regularizing ColBERT models to fix efficient ANN methods
lightonai
• • 23
Machine learning for alien climates: Introducing the ThousandWorlds benchmark
hugging-science
• • 3
Mastering Tensor Dimensions in Transformers
not-lain
• • 185
KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 352