AI Agent Skills

Meta-Transformer for Unified Multimodal Learning

Recent Transformer-based CV and related works.

A large scale non-linear optimization library

:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"