Shuai Bai

Strong 3D perception and competitive motion planning in autonomous driving are achieved without sacrificing general vision-language understanding.

Native computer use can be achieved at scale, enabling agents to outperform leading systems while significantly enhancing security against adversarial attacks.

Token-level contrastive signals can streamline reasoning processes, leading to more efficient AI models without sacrificing performance.

A single visual tokenizer in UniAR bridges the gap between understanding and generation, achieving state-of-the-art performance in image generation and editing.

Qwen-RobotNav redefines navigation by allowing real-time reconfiguration of strategies, achieving unprecedented flexibility and performance across diverse tasks.

One model to control them all: Qwen-VLA achieves impressive zero-shot generalization across diverse robotic tasks and embodiments by unifying vision-language-action modeling.

Ditch the feature extraction pipeline: GenMask directly generates segmentation masks with a diffusion transformer, achieving SOTA results by harmonizing mask and image generation in a single model.