Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR
•
51
Community Blog & Articles
Community Articles
view all
NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI
35
January 5, 2026
Introducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid Architecture
31
January 5, 2026
partnershipsnvidiarobotics
NVIDIA brings agents to life with DGX Spark and Reachy Mini
44
January 5, 2026
AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems
41
December 23, 2025
tokenizerstransformersopen-source
Tokenization in Transformers v5: Simpler, Clearer, and More Modular
- +2
109
December 18, 2025
The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator
44
December 17, 2025
CUGA on Hugging Face: Democratizing Configurable AI Agents
63
December 15, 2025
New in llama.cpp: Model Management
105
December 11, 2025
llmfine-tuningopen-source
Codex is Open Sourcing AI models
56
December 11, 2025
swifthubopen-source
Introducing swift-huggingface: The Complete Swift Client for Hugging Face
38
December 5, 2025
llmreasoningagents
DeepMath: A lightweight math reasoning Agent with smolagents
33
December 4, 2025
llmfine-tuningopen-source
Hot
We Got Claude to Fine-Tune an Open Source LLM
568
December 4, 2025
transformersv5community
Hot
Transformers v5: Simple model definitions powering the AI ecosystem
270
December 1, 2025
diffusersfluxquantization
Diffusers welcomes FLUX-2
- +4
168
November 25, 2025
NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR
•
51
Introducing Falcon H1R 7B
•
51
M2.1: Multilingual and Multi-Task Coding with Strong Generalization
•
27
The Optimal Architecture for Small Language Models
•
94
Generalist Robot Policy Evaluation in Simulation with NVIDIA Isaac Lab-Arena and LeRobot
•
18
Building Autonomous Vehicles That Reason with the NVIDIA Alpamayo Open Ecosystem
•
14
The Engineering Handbook for GRPO + LoRA with Verl: Training Qwen2.5 on Multi-GPU
•
10
Small Yet Mighty: Improve Accuracy In Multimodal Search and Visual Document Retrieval with Llama Nemotron RAG Models
•
10
Uncensor any LLM with abliteration
•
760
Red Teaming with RL: Exploiting Tinker API for Harmful RL on 235B Model
•
15
TFLOPS Gap: Why FP4 MoE Kernel Engineering Matters on Blackwell
•
9
Code a simple RAG from scratch
•
277
Qwen-Image-i2L: Training Strategies for Image-to-LoRA Generation
•
46
Understanding Low-Rank Adaptation (LoRA): A Revolution in Fine-Tuning Large Language Models
•
5
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
213
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
•
99
OpenMed: Six Months of Open-Source Medical AI and the Road Ahead
•
4
Continuity as a First-Class System Property in Artificial Intelligence
•
17
Diversity Vs Density: A data strategy comparison for fine-tuning VLMs
•
4
Why We Built VIBE Bench: Rethinking Evaluation for Real Workloads
•
4