Community Blog & Articles

Community Articles

NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt

Build specialized multimodal models with LFM3

Can we trust LLMs to judge whether a research idea is novel?

Does Your Model Run on AWS Trainium? Look It Up

Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox

Ensemble forecasting with IBM Granite time-series models

How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications

Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium.

Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster

Hugging Face ❤️ TorchTPU: TPUs, Natively

AnyLanguageModel 1.0: One Year of Local Models on Apple Platforms

MPS in PyTorch 2.15

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

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

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

Community Blog & Articles

Mundo: From seeing a place to simulating what happens there

A curriculum for post-training agents

Announcing SimReady Central: An Open Library of Simulation-Ready 3D Assets for Robotics and AI Factories

LitPivot: Developing research ideas through dynamic contextualization within the literature landscape

NVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models

NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required

Introducing A5: Proactive Personal Agent in Your Life-Long Context

Train in Simulation, Deploy on a Real Robot: Microduck with Isaac Lab 3.0

OlmoEarth v1.3: State-of-the-art embeddings for the whole planet

What's new in the hf CLI and huggingface_hub library

Pretraining a 325M Language Model from Zero on an Inference-Only NPU

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

In financial services, the AI question is moving from the model to where it runs

DecisionFormer

Uncensor any LLM with abliteration

Two Pure-Vision Pipelines at the Top of ViDoRe V3

bekko-static-embedding-v1: State-of-the-Art Retrieval for Multilingual Static Embeddings

UltraBERT: One Encoder for Classification and Retrieval

SlideOn & mSlideOn: Sparsified Late-Interaction and Dense Retrievers

Do LLM Routers Actually Route? Quick answer: Not much!

NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt

Build specialized multimodal models with LFM3

Can we trust LLMs to judge whether a research idea is novel?

Does Your Model Run on AWS Trainium? Look It Up

Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox

Ensemble forecasting with IBM Granite time-series models

How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications

Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium.

Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster

Hugging Face ❤️ TorchTPU: TPUs, Natively

AnyLanguageModel 1.0: One Year of Local Models on Apple Platforms

MPS in PyTorch 2.15

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

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

Mundo: From seeing a place to simulating what happens there

A curriculum for post-training agents

Announcing SimReady Central: An Open Library of Simulation-Ready 3D Assets for Robotics and AI Factories

LitPivot: Developing research ideas through dynamic contextualization within the literature landscape

NVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models

NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required

Introducing A5: Proactive Personal Agent in Your Life-Long Context

Train in Simulation, Deploy on a Real Robot: Microduck with Isaac Lab 3.0

OlmoEarth v1.3: State-of-the-art embeddings for the whole planet

What's new in the hf CLI and huggingface_hub library

Pretraining a 325M Language Model from Zero on an Inference-Only NPU

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

In financial services, the AI question is moving from the model to where it runs

DecisionFormer

Uncensor any LLM with abliteration

Two Pure-Vision Pipelines at the Top of ViDoRe V3

bekko-static-embedding-v1: State-of-the-Art Retrieval for Multilingual Static Embeddings

UltraBERT: One Encoder for Classification and Retrieval

SlideOn & mSlideOn: Sparsified Late-Interaction and Dense Retrievers

Do LLM Routers Actually Route? Quick answer: Not much!