Yui Home Assistant — teaching a 3B model to write Home Assistant automations that actually *work* 25 days ago
Slipstream: a benchmark for mid-flight project forecasting, and a small agent that blends the best methods 25 days ago • 1
Ink-Wash Universe: A Developer’s Chronicle of Building a Local LLM Traditional Liuyao Divination App (FateForge) at a Hackathon 25 days ago
Small Models, Bounded Jobs: Building Lesson Agent for the Hugging Face Build Small Hackathon 25 days ago • 1
Building "YourGymBuddy" – A Race Against Time, Modal Fine-Tuning, and the Power of Local AI 25 days ago • 1
Building Kids Education AI: Turning Small Models into a Complete Learning Companion for Children 26 days ago
I Built the Anti-LinkedIn — An AI Platform That Rewards Honesty, Roasts Braggarts, and Turns Your Workplace Chaos Into a Podcast 26 days ago • 1
Agentic Humanitarian Data Analyst — a small model that writes the plan before it runs the numbers 26 days ago • 1
Building Solace Space: How I Fine-Tuned a 1B LLM for Emotional Intelligence and Local Deployment 26 days ago • 1
Split-Brain Co-Pilot: local-first coding with a 1.5B browser model and a 14B verifier 26 days ago • 2
Behind the Scenes of The Grand Tribunal: Fine-Tuning Philosophers and Dynamic AI Judging 26 days ago • 2
Field Notes: Building a Chest X-ray Draft Auditor with Two Tiny 4B Models — MedGemma and NVIDIA Nemotron 27 days ago • 1
ZeroWasteKitchen: five small models, one banana curry, and what 4B parameters are actually for 27 days ago
unplug-tiny: a 22M-parameter prompt-injection firewall that tells you *where* the attack is 27 days ago • 1
Building "Wall Street of AI Agents": How I Crammed a Multi-Agent Financial Simulation into a 1B Parameter Model 28 days ago • 1
Build Small, Deploy Big Panic: How I Built DOD - Deploy or Draw for the Build Small Hackathon 29 days ago • 1
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation Paper • 2607.08741 • Published 2 days ago • 1
Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE Paper • 2607.07740 • Published 3 days ago • 7
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation Paper • 2607.08758 • Published 2 days ago • 20
WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence Paper • 2607.06838 • Published 4 days ago • 5
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Paper • 2607.07675 • Published 3 days ago • 41
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation Paper • 2607.05147 • Published 5 days ago • 27
AlayaWorld: Long-Horizon and Playable Video World Generation Paper • 2607.06291 • Published 4 days ago • 81
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding Paper • 2607.05722 • Published 4 days ago • 8
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation Paper • 2607.06558 • Published 4 days ago • 73