Blog, Articles, and discussions

Community Articles

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

and 4 others •

On the Shifting Global Compute Landscape

and 1 other •

Why Did MiniMax M2 End Up as a Full Attention Model?

The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix

Granite 4.0 Nano: Just how small can you go?

and 1 other •

What makes good reasoning data

Running Large Transformer Models on Mobile and Edge Devices

Llasa Goes RL: Training LLaSA with GRPO for Improved Prosody and Expressiveness

TorchSim: A new PyTorch-based molecular dynamics engine

Evaluate Your Own RAG: Why Best Practices Failed Us

and 4 others •

NVIDIA Isaac GR00T in LeRobot

and 4 others •

⚡ Power, Heat, and Intelligence ☁️ - AI Data Centers Explained 🏭

and 1 other •

Let's talk about LLM evaluation

Code a simple RAG from scratch

Small Language Models (SLM): A Comprehensive Overview

Aligning to What? Rethinking Agent Generalization in MiniMax M2

Ultra-Long Sequence Parallelism: Ulysses + Ring-Attention Technical Principles and Implementation

How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcare

Classement compar:IA : des votes des utilisateurs au classement participatif des modèles

KV Caching Explained: Optimizing Transformer Inference Efficiency

videodatasetsmultimodal

TimeScope: How Long Can Your Video Large Multimodal Model Go?

loradiffusionguide

Fast LoRA inference for Flux with Diffusers and PEFT

collaborationguide

Arc Virtual Cell Challenge: A Primer

multi-agentshackathongradio

Consilium: When Multiple LLMs Collaborate

researchevaluationai

Back to The Future: Evaluating AI Agents on Predicting Future Events

+3

gradiomcpcommunity

Five Big Improvements to Gradio MCP Servers

llmnlpcommunity

Seq vs Seq: the Ettin Suite of Paired Encoders and Decoders

+2

storageinfrastructurecontent addressed store

Migrating the Hub from Git LFS to Xet

lerobotroboticsmodels

Asynchronous Robot Inference: Decoupling Action Prediction and Execution

+3

agentsguicommunity

ScreenEnv: Deploy your full stack Desktop Agent

communityopen-sourcemcp

Building the Hugging Face MCP Server

roboticscommunityopen-source

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

Creating custom kernels for the AMD MI300

Upskill your LLMs with Gradio MCP Servers

Community Articles

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

and 4 others •

On the Shifting Global Compute Landscape

and 1 other •

Why Did MiniMax M2 End Up as a Full Attention Model?

The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix

Granite 4.0 Nano: Just how small can you go?

and 1 other •

What makes good reasoning data

Running Large Transformer Models on Mobile and Edge Devices

Llasa Goes RL: Training LLaSA with GRPO for Improved Prosody and Expressiveness

TorchSim: A new PyTorch-based molecular dynamics engine

Evaluate Your Own RAG: Why Best Practices Failed Us

and 4 others •

NVIDIA Isaac GR00T in LeRobot

and 4 others •

⚡ Power, Heat, and Intelligence ☁️ - AI Data Centers Explained 🏭

and 1 other •

Let's talk about LLM evaluation

Code a simple RAG from scratch

Small Language Models (SLM): A Comprehensive Overview

Aligning to What? Rethinking Agent Generalization in MiniMax M2

Ultra-Long Sequence Parallelism: Ulysses + Ring-Attention Technical Principles and Implementation

How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcare

Classement compar:IA : des votes des utilisateurs au classement participatif des modèles

KV Caching Explained: Optimizing Transformer Inference Efficiency

View all