Ye Wang

Qwen-RobotManip achieves unprecedented generalization in robotic manipulation by effectively aligning diverse data sources, outperforming existing models across multiple challenging benchmarks.

Qwen-RobotNav achieves unprecedented flexibility in navigation tasks by allowing real-time reconfiguration of its observation strategy, setting new benchmarks in the field.

Joycent synthesizes accented speech directly from standard phone sequences, eliminating the need for error-prone accented phone predictions.

Language-driven video generation in Qwen-RobotWorld achieves unprecedented accuracy in predicting robotic actions, outperforming existing models across key benchmarks.

A novel reward compilation approach boosts VLA policy success rates by over 30% in both simulated and real-world manipulation 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 garment masks: a simple human mask is all you need to nail video virtual try-on in the wild.