Kog Laneformer 2B: The Latency-First Model Behind Kog Inference Engine
kogai
• • 31Community Blog & Articles
Community Articles
view all
roboticsaicommunity
LeRobot goes to driving school: World’s largest open-source self-driving dataset
108
March 11, 2025 
communityhubllms
LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!
98
March 7, 2025 
hubpartnershipssecurity
Hugging Face and JFrog partner to make AI Security more transparent
23
March 4, 2025 
multimodalvisionvlm
A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality
78
March 4, 2025 
phoenixagentssmolagents
Trace & Evaluate your Agent with Arize Phoenix
41
February 28, 2025 
open-source-collabaudiocommunity
HuggingFace, IISc partner to supercharge model building on India's diverse languages
28
February 27, 2025 
real-timeaudiovideo
FastRTC: The Real-Time Communication Library for Python
172
February 25, 2025 
diffusersvaeinference endpoints
Remote VAEs for decoding with Inference Endpoints 🤗
41
February 24, 2025 
multimodalvision
HotSigLIP 2: A better multilingual vision language encoder
218
February 21, 2025 
vlmmultimodalvideo
HotSmolVLM2: Bringing Video Understanding to Every Device
- +3
343
February 20, 2025 
multimodalLLMvision
PaliGemma 2 Mix - New Instruction Vision Language Models by Google
75
February 19, 2025 
announcementhubinference-providers
Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥
- +3
101
February 18, 2025 
announcementhubinference-providers
Welcome Fireworks.ai on the Hub 🎆
58
February 14, 2025 
math-verifyopen-llm-leaderboardleaderboard
Fixing Open LLM Leaderboard with Math-Verify
31
February 14, 2025 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Kog Laneformer 2B: The Latency-First Model Behind Kog Inference Engine
kogai
• • 31Building Moon Bot: A Slack-Native Coding Agent Backed by HuggingFace Buckets
huggingface
• • 42Chitos: From Detection to Proof — An Autonomous Security AI That Actually Exploits
FINAL-Bench
• • 1980TB+ of astronomy for the HDD-poor: crossmatch the Multimodal Universe from your laptop
hugging-science
• • 15Does Your LLM Know *When It's About to Be Wrong*?
ginigen-ai
• • 15VLX-Flow: Continuous Video Understanding for Real-Time Multimodal Interaction
omlab
• • 13VLX-Seek: Improving VLM Fine-Grained Perception via Region Reference Instead of Coordinate Generation
omlab
• • 12VLX-Go: Vision-Language Short-Horizon Waypoint Prediction for Embodied Navigation
omlab
• • 11Which tokens does a hybrid model predict better?
allenai
• • 8KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 357Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
ibm-research
• • 36Interhuman’s Goblin: “Yeah, Friday at Five”
Interhuman
• • 7Uncensor any LLM with abliteration
mlabonne
• • 870Introducing North Mini Code: Cohere’s First Model For Developers
CohereLabs
• • 79Continuous batching for GRPO, now in TRL
sergiopaniego
• • 8How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent
nvidia
• • 67Introduction to State Space Models (SSM)
lbourdois
• • 232Code a simple RAG from scratch
ngxson
• • 352A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 33OlmoLogic: Boosting Reasoning via RLVR with Inductive Logic Programming
LukasHug
• • 3