VLANeXt: A Simple and Research-Oriented Codebase for Robotics Research
cavanloy
• • 22Community Blog & Articles
Community Articles
view all
NeoMME: an efficient Multimodal-native and Multilingual Encoder
51
September 3, 2026 
nlpguidecommunity
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
65
September 3, 2026 
agentsopen-sourcedatasets
Give Your Coding Agents a Memory You Own
30
September 3, 2026 
rlgrpotrl
Training a coding model to paint watercolours with TRL and OpenEnv
48
September 3, 2026 
Real-Time Intelligence with IBM Time Series Models on Confluent
45
September 2, 2026 
BenchMIRT: What are LLM benchmarks actually measuring?
14
September 1, 2026 
inferencejavascriptwebgpu
Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI
55
September 1, 2026 
audiospeechleaderboard
The Open ASR Leaderboard Adds Its First Global South Language
- +6
53
August 28, 2026 
nlpguidecommunity
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
120
August 26, 2026 
Granite 4.2 LLMs: How They're Built
102
August 25, 2026 
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
47
August 25, 2026 
gradioworkflowstutorial
Wire It, Run It, Deploy It: AI Workflows in Gradio
43
August 25, 2026 
researchsearchembeddings
How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code
30
August 21, 2026 
audiospeechbenchmark
Measuring benchmark optimization in speech recognition
- +3
65
August 21, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
VLANeXt: A Simple and Research-Oriented Codebase for Robotics Research
cavanloy
• • 22Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States
KangLiao
• • 22Technical writing in the agentic era
joelniklaus
• • 15Evaluating LLMs Under Production Parity: A Replay Pipeline for Safe Model Swapping in Conversational Agents
TechforHumans
• • 12Internet-Scale Knowledge Retrieval: A Novel Vector Search Dataset at 10B Scale
Qdrant
• • 12Uncensor any LLM with abliteration
mlabonne
• • 914Did the Civilization Emerge, or Was It Recited?
FINAL-Bench
• • 9KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 406Cosmos-Reason2 on a Quest 3: Performance, Cost, and What Compression Actually Buys You
ErenAta00
• • 8Inside three.ws: The Open-Source Stack That Gives AI Agents a Body, a Brain, a Wallet, and a Job
three-ws
• • 47Open Yap 1K: 1,000 hours of full-duplex natural conversation, free for commercial use
TheAgenticDataCompany
• • 6From Zero to Hero: An Open LLM Ecosystem for Armenian
osoblanco
• • 6VLM Run Gateway: Run open-weight OCR, VLM and vision models behind one API
vlm-run
• • 5Deploy local agents everywhere with LFM2.5-2.6B
LiquidAI
• • 96Modern LLMs: What the FLIP is an Engram!?
Blackroot
• • 13Frontier-Assisted Single-Prompt Disposable Risk Assessment
darkc0de
• • 4Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC
ibm-granite
• • 33From watching AI-Generated worlds to exploring them with H3
zuanfilm
• • 3DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
NormalUhr
• • 299How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons
sherryxychen
• • 82