#Open Source

Ant Group open-sourced LingBot-Video, the world's first mixture-of-experts (MoE) based embodied video foundation model for robotics, achieving a state-of-the-art score of 0.620 on the RBench benchmark. The model is released under Apache 2.0 license on GitHub. This open-source release significantly lowers the barrier for embodied AI research, providing a highly efficient MoE architecture that activates only 3B of 30B total parameters, making it three times more efficient than dense models of similar size. It can accelerate progress in robot action prediction, simulation data generation, and world model development. LingBot-Video innovates in three aspects: architecture (DiT+MoE for capacity-cost balance), data (70K hours of embodied data covering dexterous manipulation, robot locomotion, and egocentric interaction), and training (multi-dimensional reinforcement learning rewards focusing on physical plausibility and task completion). The model uses a Diffusion Transformer (DiT) backbone.

Git 2.55.0 has been released, featuring an experimental 'git history' command with new capabilities and the addition of the fsmonitor daemon for Linux systems. The release includes non-merge commits from 100 people, 33 of whom are first-time contributors. This release brings performance improvements for Linux users through the fsmonitor daemon, which can significantly speed up commands like 'git status'. The enhanced 'git history' command provides a more interactive way to review and modify commit history, increasing developer productivity. The fsmonitor daemon works by watching the working directory for file changes, allowing Git to avoid scanning the entire tree. The 'git history' command remains experimental; users should be aware that its interface may change in future releases.