NEO-unify: Building Native Multimodal Unified Models End to End
•
65
Community Blog & Articles
Community Articles
view all
Bringing Robotics AI to Embedded Platforms: Dataset Recording, VLA Fine‑Tuning, and On‑Device Optimizations
5
March 5, 2026 
open-sourcediffusersgenerative
Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines
15
March 5, 2026 
PRX Part 3 — Training a Text-to-Image Model in 24h!
49
March 3, 2026 
mixture-of-expertsoptimizationtransformers
Mixture of Experts (MoEs) in Transformers
- +3
121
February 26, 2026 
communityopen-sourcellm
HotGGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +2
479
February 20, 2026 
llmfine-tuningtraining
Train AI models with Unsloth and Hugging Face Jobs for FREE
- +2
81
February 20, 2026 
IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST
18
February 18, 2026 
gradioclaudehtml
One-Shot Any Web App with Gradio's gr.HTML
25
February 18, 2026 
open-sourcecudakernels
Custom Kernels for All from Codex and Claude
67
February 13, 2026 
announcementopen-sourcecommunity
OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environments
- +1
30
February 12, 2026 
announcementtransformers.jstransformers
Transformers.js v4 Preview: Now Available on NPM!
75
February 9, 2026 
Introducing SyGra Studio
25
February 5, 2026 
evaluationleaderboardcommunity
Community Evals: Because we're done trusting black-box leaderboards over the community
-
-
- +3
85
February 4, 2026 
H Company's new Holo2 model takes the lead in UI Localization
5
February 3, 2026 NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
NEO-unify: Building Native Multimodal Unified Models End to End
•
65
The ML Engineer's Guide to Protein AI
•
20
TiRex on the Edge
•
10
Forge: Scalable Agent RL Framework and Algorithm
•
134
Deploying Open Source Vision Language Models (VLM) on Jetson
•
33
Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework
•
8
Getting More from Your Test-Time Compute Budget with Portfolio Beam Search
•
7
We’re open-sourcing our text-to-image model and the process behind it
•
92
Bringing Autonomous Driving RL to OpenEnv and TRL
•
21
LLM Architectures Explained: What Powers Today’s Top Models
•
7
From GRPO to DAPO and GSPO: What, Why, and How
•
94
Building Tucano 2: Open-Source Language Models That Actually _Think_ in Portuguese
•
6
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
238
easytranscriber: Speech Recognition with Accurate Timestamps in the HF Ecosystem
•
5
Introducing Kanon 2 Enricher — the world’s first hierarchical graphitization model
•
5
Uncensor any LLM with abliteration
•
791
Code a simple RAG from scratch
•
306
Text-to-image Architectural Experiments
•
52
De-mystifying Multimodal Learning: The Hidden Inefficiency in Vision Language Modelling
•
4
Create, Evaluate, and Connect AI Skills | SkillNet: A Large-Scale Agentic "Skill Graph" Knowledge Base
•
11