Meta Chinese Researcher Releases ATLAS for Generalizable Visual Reasoning with One Word

Meta华人发布ATLAS，一个词搞定可泛化的视觉推理！

Meta AI and the Chinese University of Hong Kong proposed ATLAS, a visual reasoning method that uses one Functional Token to connect Agentic and Latent Visual Reasoning, with ATLAS-178K, a two-stage SFT+RL pipeline, and LA-GRPO to train sparse visual-operation tokens.

Why it matters: HKR-H/K/R pass: the one-token angle is clickable, and the post gives dataset and training details. As a Meta AI/CUHK research release rather than a flagship model or product launch, it fits the 78–84 band.