Chengju Liu

Achieving $0.1\text{m}$ spatial resolution with real-time inference, GaussianSeed redefines the efficiency-quality balance in 3D occupancy prediction.

RynnBrain 1.1 not only outperforms all competitors in embodied cognition tasks but also redefines how robots can be trained for complex manipulation through innovative 3D grounding techniques.

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.

RynnBrain leapfrogs existing embodied foundation models, offering a unified, open-source spatiotemporal model that excels at physically grounded reasoning and planning across a wide range of benchmarks.