NEO-unify: Building Native Multimodal Unified Models End to End
•
75
Community Blog & Articles
Community Articles
view all
open-sourcecudakernels
Custom Kernels for All from Codex and Claude
69
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!
76
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
88
February 4, 2026 
H Company's new Holo2 model takes the lead in UI Localization
5
February 3, 2026 
The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+
51
February 3, 2026 
Training Design for Text-to-Image Models: Lessons from Ablations
69
February 3, 2026 
gradiodaggr
Introducing Daggr: Chain apps programmatically, inspect visually
-
- +1
103
January 29, 2026 
upskillagent-skillsagentic
We Got Claude to Build CUDA Kernels and teach open models!
148
January 28, 2026 
Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek
45
January 27, 2026 
Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs
24
January 27, 2026 
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
64
January 27, 2026 
AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial Reality
31
January 21, 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
•
75
The ML Engineer's Guide to Protein AI
•
24
TiRex on the Edge
•
12
MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning
•
11
Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework
•
10
Uncensor any LLM with abliteration
•
796
From GRPO to DAPO and GSPO: What, Why, and How
•
99
We’re open-sourcing our text-to-image model and the process behind it
•
93
Building Tucano 2: Open-Source Language Models That Actually _Think_ in Portuguese
•
8
LLM Architectures Explained: What Powers Today’s Top Models
•
8
Konkani LLM: Bringing a Multi-Script Low-Resource Language to the AI Era
•
7
Deploying Open Source Vision Language Models (VLM) on Jetson
•
33
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
240
Text-to-image Architectural Experiments
•
53
Forge: Scalable Agent RL Framework and Algorithm
•
136
Kanon 2 Reranker: the most powerful reranker for legal RAG
•
5
Code a simple RAG from scratch
•
306
Getting More from Your Test-Time Compute Budget with Portfolio Beam Search
•
8
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
•
12