Introduction to Trimming ✂
lbourdois
• • 36Community Blog & Articles
Community Articles
view all
Direct Preference Optimization Beyond Chatbots
1
June 3, 2026 
guideroboticsreachy
Adding MCP Tools to Reachy Mini
5
June 3, 2026 Holo3.1: Fast & Local Computer Use Agents
24
June 2, 2026 
Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains
21
June 1, 2026 
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
79
June 1, 2026 
Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action
62
June 1, 2026 
torchprofileCUDA
Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler
- +1
72
May 29, 2026 
guideroboticsaudio
Reachy Mini goes fully local
50
May 27, 2026 
llmrltrl
Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL
- +4
38
May 27, 2026 
agentsllmsguide
Harness, Scaffold, and the AI Agent Terms Worth Getting Right
96
May 25, 2026 
OlmoEarth v1.1: A more efficient family of Earth observation models
22
May 19, 2026 
nlpcommunityresearch
Introducing the Ettin Reranker Family
50
May 19, 2026 
PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend
35
May 18, 2026 Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality
32
May 14, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Introduction to Trimming ✂
lbourdois
• • 36ClawHub Security Signals: Large Corpus Multi-Scanner Dataset for Agent Skill Security Research
OpenClaw
• • 15LeRobot Humanoid: An Open, Low-Cost, 3D-Printed Humanoid for Robot Learning
VirgileBatto
• • 54Agentic RL: Token-In, Token-Out Done Right
huggingface
• • 11MONET: Lowering the bar for World-Class Image Generation research.
jasperai
• • 10Dell Enterprise Hub at Dell Tech World 2026: new models, new platforms, faster to production
balaatdell
• • 9Taking Alpamayo to New Heights with Driving Foundation Models and Closed-Loop Training
drmapavone
• • 9ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM
ibm-research
• • 14Server is at capacity
ml-intern-explorers
• • 6Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models
nvidia
• • 29Give your agents ZeroGPU to ship viral AI apps autonomously
victor
• • 6MiniMax Goes Sparse: Decoding M3's Attention from a Single Diagram
AtlasCloud-AI
• • 5Mastering Tensor Dimensions in Transformers
not-lain
• • 179Tokenization is Killing our Multilingual LLM Dream
omarkamali
• • 12A Deep Neural Network that turns Any Image into a Playable Game! All on consumer GPUs, NOT DATACENTER
lucidml
• • 4Uncensor any LLM with abliteration
mlabonne
• • 863Code a simple RAG from scratch
ngxson
• • 338Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
NormalUhr
• • 126From Data Repositories to Production Data Pipelines: Bridging Hugging Face Datasets and Dagster with dagster-hf-datasets
AINovice2005
• • 3AutoResearch on Diffusers' Pipeline for 10 Rounds on JarvisLabs
chansung
• • 3