CRAFT: Continuous Reasoning and Agentic Feedback Tuning
•
66
Community Blog & Articles
Community Articles
view all
announcementtransformers.jstransformers
Transformers.js v4 Preview: Now Available on NPM!
51
February 9, 2026
Introducing SyGra Studio
17
February 5, 2026
Nemotron ColEmbed V2: Raising the Bar for Multimodal Retrieval with ViDoRe V3’s Top Model
25
February 4, 2026
evaluationleaderboardcommunity
Community Evals: Because we're done trusting black-box leaderboards over the community
- +3
63
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+
37
February 3, 2026
Training Design for Text-to-Image Models: Lessons from Ablations
56
February 3, 2026
gradiodaggr
Introducing Daggr: Chain apps programmatically, inspect visually
-
- +1
97
January 29, 2026
upskillagent-skillsagentic
We Got Claude to Build CUDA Kernels and teach open models!
134
January 28, 2026
Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek
42
January 27, 2026
Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs
20
January 27, 2026
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
51
January 27, 2026
AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial Reality
31
January 21, 2026
One Year Since the “DeepSeek Moment”
55
January 20, 2026
NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
CRAFT: Continuous Reasoning and Agentic Feedback Tuning
•
66
From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output
•
18
🚀 DTS: A Candidate for the Best Parallel Reasoning in LLMs
•
12
🚀 SyGra V2.0.0
•
8
Uncensor any LLM with abliteration
•
772
Code a simple RAG from scratch
•
296
LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family
•
81
Training Qwen3 VL to label bbox : synthetic data, environment and training analysis
•
5
Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face
•
104
Decoding Strategies in Large Language Models
•
107
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
232
Small Language Models (SLM): A Comprehensive Overview
•
130
Why SGLang is a Game-Changer for LLM Workflows
•
17
From GRPO to DAPO and GSPO: What, Why, and How
•
84
We’re open-sourcing our text-to-image model and the process behind it
•
85
EuroLLM-22B
•
46
Introducing NVIDIA Cosmos Policy for Advanced Robot Control
•
38
Building a Mood-Based Movie Recommendation Engine with Voyage-4-nano, Hugging Face, and MongoDB Atlas Vector Search
•
3
Enabling Large Scale RLHF of GPTOSS with Megatron backend in VeRL
•
3
Rank-Stabilized LoRA: Unlocking the Potential of LoRA Fine-Tuning
•
32