Data-Efficient RLVR via Off-Policy Influence Guidance Paper β’ 2510.26491 β’ Published Oct 30 β’ 9
Running on CPU Upgrade Featured 2.53k The Smol Training Playbook π 2.53k The secrets to building world-class LLMs
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models Paper β’ 2508.06471 β’ Published Aug 8 β’ 192
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models Paper β’ 2508.06471 β’ Published Aug 8 β’ 192
Qwen/Qwen3-Coder-480B-A35B-Instruct Text Generation β’ 480B β’ Updated Aug 21 β’ 196k β’ β’ 1.25k