Blog, Articles, and discussions

Community Articles

Visualizing How VLMs Work

and 1 other •

mem-agent: Equipping LLM Agents with Memory Using RL

and 1 other •

BigCodeArena: Judging code generations end to end with code executions

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

Model statistics of the 50 most downloaded entities on Hugging Face

about 6 hours ago

Ethics + Sustainability = Responsible AI

and 1 other •

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

and 8 others •

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

and 4 others •

about 6 hours ago

Uncensor any LLM with abliteration

ModernVBERT: Towards Smaller Visual Document Retrievers

and 4 others •

Small Language Models (SLM): A Comprehensive Overview

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

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

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

Code a simple RAG from scratch

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

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Mastering Tensor Dimensions in Transformers

Everything You Need to Know about Knowledge Distillation

and 1 other •

Combining GRPO and RAG for Explainable Financial Predictions

nlpevaluationretrieval

Introducing RTEB: A New Standard for Retrieval Evaluation

+2

October 1, 2025

agentsjupyterllm

Jupyter Agents: training LLMs to reason with notebooks

September 10, 2025

llmnlpcommunity

mmBERT: ModernBERT goes Multilingual

+2

September 9, 2025

mcpresearchguide

MCP for Research: How to Connect AI to Research Tools

August 18, 2025

researchllmevaluation

TextQuests: How Good are LLMs at Text-Based Video Games?

August 12, 2025

researchgradioopen-source

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

+1

researchevaluationai

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

+3

llmnlpcommunity

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

+2

Efficient MultiModal Data Pipeline

+1

llmnlpreasoning

SmolLM3: smol, multilingual, long-context reasoner

+19

Gemma 3n fully available in the open-source ecosystem!

+4

nanoVLM: The simplest repository to train your VLM in pure PyTorch

+3

vlmvisionmultimodal

Vision Language Models (Better, Faster, Stronger)

+1

long-contextbenchmarknlp

Introducing HELMET

+3

Community Articles

Visualizing How VLMs Work

and 1 other •

mem-agent: Equipping LLM Agents with Memory Using RL

and 1 other •

BigCodeArena: Judging code generations end to end with code executions

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

Model statistics of the 50 most downloaded entities on Hugging Face

about 6 hours ago

Ethics + Sustainability = Responsible AI

and 1 other •

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

and 8 others •

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

and 4 others •

about 6 hours ago

Uncensor any LLM with abliteration

ModernVBERT: Towards Smaller Visual Document Retrievers

and 4 others •

Small Language Models (SLM): A Comprehensive Overview

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

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

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

Code a simple RAG from scratch

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

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Mastering Tensor Dimensions in Transformers

Everything You Need to Know about Knowledge Distillation

and 1 other •

Combining GRPO and RAG for Explainable Financial Predictions

View all