UI-Mate Collection Open-weight CUA models and office-centric CUA benchmark • 4 items • Updated 7 days ago • 21
DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration Paper • 2606.03103 • Published Jun 2 • 3
Running 4.05k The Ultra-Scale Playbook 🌌 4.05k The ultimate guide to training LLM on large GPU Clusters
Guided Self-Evolving LLMs with Minimal Human Supervision Paper • 2512.02472 • Published Dec 2, 2025 • 55
From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence Paper • 2511.18538 • Published Nov 23, 2025 • 307
The End of Manual Decoding: Towards Truly End-to-End Language Models Paper • 2510.26697 • Published Oct 30, 2025 • 121