Nemotron-Cascade 2 Collection Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation • 4 items • Updated 1 day ago • 53
Running on CPU Upgrade 627 The Ultimate MoE Training Handbook 🧩 627 A hands-on guide to training Mixture-of-Experts models
StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions Paper • 2610.17309 • Published Oct 12 • 30
Jev-style decision models: open data Collection Data for Jev-style decision models. Notes say where labels come from: humans, exact rules or an LLM teacher. Last updated 2026-10-23. • 20 items • Updated 22 days ago • 10
view article Article GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval chungimungi • Aug 8 • 13