Yan Huang

Current action-conditioned world models are limited by their reliance on visual patterns, failing to generalize physical dynamics across different robot embodiments.

Memory-augmented manipulation models can now achieve state-of-the-art performance while remaining data-efficient and generalizable across diverse tasks and environments.

Local Margin Restoration not only shields VLMs from bias but also preserves their semantic integrity, leading to superior performance in dynamic environments.

FreeShadow achieves realistic shadow removal without any training, leveraging diffusion models to generalize effectively across diverse scenarios.

Trustworthiness in embodied intelligence isn't just about performance; it's about managing risk across a multi-layered framework that ensures safety and reliability in real-world applications.

Kimi K3's innovative architecture achieves a 2.5x scaling efficiency improvement, enabling robust performance across diverse long-horizon tasks.