Qijun Chen

Memory-augmented pose estimation can dramatically improve generalization across diverse object instances, outperforming traditional methods by leveraging accumulated geometric knowledge.

TACO achieves state-of-the-art performance in open-vocabulary video recognition by preserving out-of-distribution alignment, challenging the conventional trade-off between generalization and specialization.

KinematicRL bridges the sim-to-real gap in social navigation by leveraging higher-order control and a streamlined human tracking system, yielding robust real-world performance.

Learning dynamics through outcomes rather than parameters leads to significantly more robust policy adaptation in the face of real-world changes.

Autonomous driving systems can now learn continuously without forgetting, thanks to a new method that disentangles true driving skills from spurious correlations caused by sensor noise and environmental changes.