Community Blog & Articles

Community Articles

TorchNeuron: running HF models on AWS Trainium is easier than ever

Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline

Welcome Beam: a 501B open model you can own, customize, and scale

Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint

Apertus 1.5 Release Notes

Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta

Welcome FLUX.3 Image Klein in Diffusers

HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the cost

Run fast, private agents on-device with LFM2.5-24B-A2B

The model that didn't exist, so you made it yourself

Introducing Falcon ASR

The Agent Said It Was Done. The Database Disagreed.

AutoSynthData: Generating Training Data for Enterprise Agents

Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning

NEW Articles from Team or Enterprise organizations will get promoted to the main section.

Community Blog & Articles

UltraBERT: One Encoder for Classification and Retrieval

The Missing Piece in LLM Memory: Why Long Context and Retrieval Aren't Enough for Belief Revision

Tokenmaxxing BERT: 50x faster tokenization

Introducing Lumma-Fev-27B

Impactful scheduling for GPU clusters

One Decision Model Instead of a Ranking Team: Short-Video and News Recommendation with autotrust/JEV-27B-VL

When agents self-improve, what should persist?

Backpropagation on an Inference-Only NPU: Pretraining VKORE-46M-NPU From Scratch

Fine-Tune ASR for Your Domain with NVIDIA Speech Agent Skills

ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third

SlideOn & mSlideOn: Sparsified Late-Interaction and Dense Retrievers

Introducing Llama Windows: llama.cpp in your Windows tray

LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model

UIBK-Embedding-v1: A Dense and a Late-Interaction Retriever in One Model, One Index and One Search

New in llama.cpp: Decision Models

Sort your prompts: a free speed-up for MoE batch inference

Estimating physics from images: what real measurements reveal

NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction

QVAC TranscribePsy: State-of-the-Art On-Device Multilingual Speech Recognition

Extending Nemotron 3.5 Super 120B VL with Agentic Web Development Capabilities

TorchNeuron: running HF models on AWS Trainium is easier than ever

Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline

Welcome Beam: a 501B open model you can own, customize, and scale

Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint

Apertus 1.5 Release Notes

Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta

Welcome FLUX.3 Image Klein in Diffusers

HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the cost

Run fast, private agents on-device with LFM2.5-24B-A2B

The model that didn't exist, so you made it yourself

Introducing Falcon ASR

The Agent Said It Was Done. The Database Disagreed.

AutoSynthData: Generating Training Data for Enterprise Agents

Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning

UltraBERT: One Encoder for Classification and Retrieval

The Missing Piece in LLM Memory: Why Long Context and Retrieval Aren't Enough for Belief Revision

Tokenmaxxing BERT: 50x faster tokenization

Introducing Lumma-Fev-27B

Impactful scheduling for GPU clusters

One Decision Model Instead of a Ranking Team: Short-Video and News Recommendation with autotrust/JEV-27B-VL

When agents self-improve, what should persist?

Backpropagation on an Inference-Only NPU: Pretraining VKORE-46M-NPU From Scratch

Fine-Tune ASR for Your Domain with NVIDIA Speech Agent Skills

ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third

SlideOn & mSlideOn: Sparsified Late-Interaction and Dense Retrievers

Introducing Llama Windows: llama.cpp in your Windows tray

LightOnOCR-3: High-Performance OCR and Layout Extraction in One Model

UIBK-Embedding-v1: A Dense and a Late-Interaction Retriever in One Model, One Index and One Search

New in llama.cpp: Decision Models

Sort your prompts: a free speed-up for MoE batch inference

Estimating physics from images: what real measurements reveal

NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction

QVAC TranscribePsy: State-of-the-Art On-Device Multilingual Speech Recognition

Extending Nemotron 3.5 Super 120B VL with Agentic Web Development Capabilities