Jianfei Yang

Quality-aware pretraining strategies, particularly approach-aware episode conditioning, can significantly outperform plain behavioral cloning in VLA tasks, with optimal choices depending on label granularity and model architecture.

Assistive robots no longer require invasive visual cameras to track human gestures, successfully executing closed-loop manipulation through physical privacy curtains via mmWave radar and state-space temporal modeling.

Real-world robot failures can be autonomously converted into interactive digital twins for targeted RL, boosting out-of-distribution manipulation by 18.75% while completely bypassing manual teleoperated recovery.

Robots can achieve remarkable generalization in unpredictable environments using a lightweight feedback mechanism, even with minimal training data.

Achieving state-of-the-art performance in scene understanding and controllable 4D generation, GaussianDWM++ redefines how we integrate language and 3D scene editing.

UCA-Flow achieves a remarkable 9.3% increase in action success rates while being up to 45.6 times faster than previous approaches.

RynnValue shows that using temporal distance as a supervision target can outperform traditional preference-based methods in robotic learning, achieving higher accuracy and broader generalization.