Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States
KangLiao
• • 23Community Blog & Articles
Community Articles
view all
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic
10
September 8, 2026 
NeoMME: an efficient Multimodal-native and Multilingual Encoder
85
September 3, 2026 
nlpguidecommunity
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
84
September 3, 2026 
agentsopen-sourcedatasets
Give Your Coding Agents a Memory You Own
58
September 3, 2026 
rlgrpotrl
Training a coding model to paint watercolours with TRL and OpenEnv
58
September 3, 2026 
Real-Time Intelligence with IBM Time Series Models on Confluent
49
September 2, 2026 
BenchMIRT: What are LLM benchmarks actually measuring?
18
September 1, 2026 
inferencejavascriptwebgpu
Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI
59
September 1, 2026 
audiospeechleaderboard
The Open ASR Leaderboard Adds Its First Global South Language
- +6
56
August 28, 2026 
nlpguidecommunity
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
123
August 26, 2026 
Granite 4.2 LLMs: How They're Built
107
August 25, 2026 
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
49
August 25, 2026 
gradioworkflowstutorial
Wire It, Run It, Deploy It: AI Workflows in Gradio
44
August 25, 2026 
researchsearchembeddings
How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code
31
August 21, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States
KangLiao
• • 23Making open-source AI weather forecasting models easy to run
hugging-science
• • 20Internet-Scale Knowledge Retrieval: A Novel Vector Search Dataset at 10B Scale
Qdrant
• • 14Open Yap 1K: 1,000 hours of full-duplex natural conversation, free for commercial use
TheAgenticDataCompany
• • 11TranslatePsy-AfriSLM: Optimized Machine Translation for African Languages
qvac
• • 12KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 408Cosmos-Reason2 on a Quest 3: Performance, Cost, and What Compression Actually Buys You
ErenAta00
• • 8From Zero to Hero: An Open LLM Ecosystem for Armenian
osoblanco
• • 7VLM Run Gateway: Run open-weight OCR, VLM and vision models behind one API
vlm-run
• • 6Uncensor any LLM with abliteration
mlabonne
• • 915Inside three.ws: The Open-Source Stack That Gives AI Agents a Body, a Brain, a Wallet, and a Job
three-ws
• • 47TurboQuant Quantization Explained
lucifertrj
• • 5VLANeXt: A Simple and Research-Oriented Codebase for Robotics Research
cavanloy
• • 22Technical writing in the agentic era
joelniklaus
• • 16A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 47A Real-World Dataset for Noise-Robust Speech AI: 100+ Timestamped Noise Types Across 58 Indian Languages
ARTPARK-IISc
• • 3From GRPO to DAPO and GSPO: What, Why, and How
NormalUhr
• • 143How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons
sherryxychen
• • 82Scaling Pedagogical Pre-training: From Optimal Mixing to 10 Billion Tokens
codelion
• • 7NEO-unify: Building Native Multimodal Unified Models End to End
sensenova
• • 181