Apple's research team published an arXiv paper detailing HALO, a humanoid robot autonomy stack that layers a VLM task orchestrator, a DiT motion generator, and a reinforcement-learning tracker, deployed on a Unitree G1 with an onboard Mac mini for inference. Across 360 single-task trials in six previously unmapped real environments, HALO averaged a 91% success rate, though long-horizon composite tasks fell to 70% and the hardest combination to 50%. The team also open-sourced the data generation, training, and deployment code.
Diffusion Transformer
DiT
Diffusion models that use Transformer architectures as their backbone.
Curated Intelligence
Digital artist Karim Joseph Nassar launched 'Vathography,' an art practice leveraging the Marigold V2 model. The project uses diffusion transformers to infer depth from single photographs, translating visual data into volumetric images to explore new expressive forms beyond traditional photography.
Zhipu AI and Huawei have open-sourced GLM-Image, a new multimodal model fully trained on Ascend Atlas 800T A2 chips using the MindSpore framework, validating domestic hardware for frontier AI. The model employs a hybrid 'autoregressive + diffusion decoder' architecture, achieving state-of-the-art performance in complex text rendering (especially Chinese characters) with ultra-low inference costs.