Chenxi Liu

A new method improves how self-driving cars detect objects using LiDAR.

Integrating language models into causal discovery streamlines analysis and reveals hidden relationships.

LightTR enhances trajectory recovery using federated learning while protecting user privacy.

A new method enhances image representation by identifying discontinuities during processing.

Enhancing Llama-3's capabilities with improved language mixture and training methods.

A new approach to reduce inaccuracies in language models using skepticism.

LoRA transforms artistic style adaptation into a simple process.