How We Built a Semantic Highlight Model To Save Token Cost for RAG
•
36
Community Blog & Articles
Community Articles
view all
Introducing OptiMind, a research model designed for optimization
14
January 15, 2026
open-responsesresponsesopen-source
Open Responses: What you need to know
57
January 15, 2026
NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI
52
January 5, 2026
Introducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid Architecture
35
January 5, 2026
partnershipsnvidiarobotics
NVIDIA brings agents to life with DGX Spark and Reachy Mini
53
January 5, 2026
AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems
45
December 23, 2025
tokenizerstransformersopen-source
Tokenization in Transformers v5: Simpler, Clearer, and More Modular
- +2
114
December 18, 2025
The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator
45
December 17, 2025
CUGA on Hugging Face: Democratizing Configurable AI Agents
65
December 15, 2025
New in llama.cpp: Model Management
108
December 11, 2025
llmfine-tuningopen-source
Codex is Open Sourcing AI models
62
December 11, 2025
swifthubopen-source
Introducing swift-huggingface: The Complete Swift Client for Hugging Face
39
December 5, 2025
llmreasoningagents
DeepMath: A lightweight math reasoning Agent with smolagents
34
December 4, 2025
llmfine-tuningopen-source
Hot
We Got Claude to Fine-Tune an Open Source LLM
575
December 4, 2025
NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
How We Built a Semantic Highlight Model To Save Token Cost for RAG
•
36
🥃 Distilling Tiny Embeddings
•
16
The Optimal Architecture for Small Language Models
•
108
SmolLM-Smashed: Tiny Giants, Optimized for Speed
•
10
Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR
•
62
Proof of Time: A Benchmark for Evaluating Scientific Idea Judgments
•
8
Introducing Falcon H1R 7B
•
58
M2.1: Multilingual and Multi-Task Coding with Strong Generalization
•
33
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
218
Small Language Models (SLM): A Comprehensive Overview
•
122
VLM-OCR Recipes on GPU Infrastructure
•
5
Small Yet Mighty: Improve Accuracy In Multimodal Search and Visual Document Retrieval with Llama Nemotron RAG Models
•
15
Beyond Brute Force: Why LoongFlow is the “Thinking” Evolution of OpenEvolve
•
4
makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch
•
115
Uncensor any LLM with abliteration
•
763
ColPali: Efficient Document Retrieval with Vision Language Models 👀
•
310
The Large Language Model Course
•
217
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
•
102
Common AI Model Formats
•
61
From Image-to-LoRA to In-Context Edit
•
7