Blog, Articles, and discussions

NEW 你也可以阅读这篇博客的中文版

Community Articles

mem-agent: Equipping LLM Agents with Memory Using RL

and 1 other •

Model statistics of the 50 most downloaded entities on Hugging Face

Visualizing How VLMs Work

and 1 other •

How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons

BigCodeArena: Judging code generations end to end with code executions

Granite Embedding R2: Setting New Standards for Enterprise Retrieval

about 20 hours ago

Ethics + Sustainability = Responsible AI

and 1 other •

High-Quality Datasets for Far-Field ASR (Treble Technologies x Hugging Face)

and 4 others •

Ring-flash-linear-2.0: A Highly Efficient Hybrid Architecture for Test-Time Scaling

and 8 others •

Nemotron-Personas-India: Synthesized Data for Sovereign AI

and 6 others •

Uncensor any LLM with abliteration

Code a simple RAG from scratch

Small Language Models (SLM): A Comprehensive Overview

Reactive Transformer (RxT): Fixing the Memory Problem in Conversational AI

🛠 ML-Agents Tips & Lessons Learned (AutoMind + MLE-Bench)

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

Everything You Need to Know about Knowledge Distillation

and 1 other •

From GRPO to DAPO and GSPO: What, Why, and How

How to Train an Antibody Developability Model

and 1 other •

There is no such thing as a tokenizer-free lunch

inteloptimumquantization

Get your VLM running in 3 simple steps on Intel CPUs

+1

October 15, 2025

SOTA OCR on-device with Core ML and dots.ocr

October 2, 2025

nlpevaluationretrieval

Introducing RTEB: A New Standard for Retrieval Evaluation

+2

October 1, 2025

guideopen-sourcegeneration

VibeGame: Exploring Vibe Coding Games

September 29, 2025

Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models

+1

September 29, 2025

swifttransformersswift-transformers

Swift Transformers Reaches 1.0 — and Looks to the Future

September 26, 2025

Smol2Operator: Post-Training GUI Agents for Computer Use

+1

September 23, 2025

leaderboardsgaiaagents

Gaia2 and ARE: Empowering the community to study agents

+5

September 22, 2025

llmsinference-providersscaleway

Scaleway on Hugging Face Inference Providers 🔥

+5

September 19, 2025

llmssecuritypartnerships

Democratizing AI Safety with RiskRubric.ai

September 18, 2025

llmsinference-providerspublic-ai

Public AI on Hugging Face Inference Providers 🔥

+2

September 17, 2025

lerobotdatasetsrobotics

`LeRobotDataset`: Bringing large-scale datasets to lerobot

+7

September 16, 2025

ethicstext-generationguide

Visible Watermarking with Gradio

September 15, 2025

transformerspytorchoptimization

Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

+3

September 11, 2025

Community Articles

mem-agent: Equipping LLM Agents with Memory Using RL

and 1 other •

Model statistics of the 50 most downloaded entities on Hugging Face

Visualizing How VLMs Work

and 1 other •

How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons

BigCodeArena: Judging code generations end to end with code executions

Granite Embedding R2: Setting New Standards for Enterprise Retrieval

about 20 hours ago

Ethics + Sustainability = Responsible AI

and 1 other •

High-Quality Datasets for Far-Field ASR (Treble Technologies x Hugging Face)

and 4 others •

Ring-flash-linear-2.0: A Highly Efficient Hybrid Architecture for Test-Time Scaling

and 8 others •

Nemotron-Personas-India: Synthesized Data for Sovereign AI

and 6 others •

Uncensor any LLM with abliteration

Code a simple RAG from scratch

Small Language Models (SLM): A Comprehensive Overview

Reactive Transformer (RxT): Fixing the Memory Problem in Conversational AI

🛠 ML-Agents Tips & Lessons Learned (AutoMind + MLE-Bench)

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

Everything You Need to Know about Knowledge Distillation

and 1 other •

From GRPO to DAPO and GSPO: What, Why, and How

How to Train an Antibody Developability Model

and 1 other •

There is no such thing as a tokenizer-free lunch

View all