HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing Paper • 2602.03560 • Published Feb 3 • 46
LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model Paper • 2509.00676 • Published Aug 31, 2025 • 85
Running Featured 1.31k FineWeb: decanting the web for the finest text data at scale 🍷 1.31k Generate a curated web‑text dataset for LLM training
Running 3.74k The Ultra-Scale Playbook 🌌 3.74k The ultimate guide to training LLM on large GPU Clusters
MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining Paper • 2505.07608 • Published May 12, 2025 • 82