Laguna S 2.1 Collection Our most capable model to date, designed for long-horizon work. • 12 items • Updated 9 days ago • 38
view article Article Training a 2.7B MoE from scratch for $200, one GPU at a time vovaRL • 2 days ago • 3
view article Article Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident +2 hlarcher, XciD, raphael-gl, chris-rannou • 5 days ago • 374
Direct Preference Optimization: Your Language Model is Secretly a Reward Model Paper • 2305.18290 • Published May 29, 2023 • 68
My models: daily driver rotation Collection A rotating list of models I created and currently use as daily drivers. From my many models, these are the ones I’m actively using. • 4 items • Updated 5 days ago • 10
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models Paper • 2606.03748 • Published Jun 2 • 22
SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training Paper • 2605.18719 • Published May 18 • 7