Shaokang Cheng

Papers

Total Citations

H-Index

About

Shaokang Cheng is a rising researcher at the forefront of trajectory prediction, a critical domain bridging computer vision, machine learning, and robotics. His work focuses on addressing the fundamental challenge of long-term trajectory forecasting, where uncertainty compounds over time. Cheng’s key contributions center on integrating knowledge distillation with advanced sequence modeling to enhance prediction accuracy and robustness. In his 2024 paper "Distilling Knowledge for Short-to-Long Term Trajectory Prediction" (7 citations), he pioneered a framework that transfers knowledge from short-term models to improve long-term forecasts, tackling the inherent unpredictability of extended time horizons. Building on this, his 2025 work "KD-Mamba: Selective state space models with knowledge distillation for trajectory prediction" (6 citations) introduces a novel architecture that combines selective state space models with distillation techniques, achieving state-of-the-art performance. Though early in his career, Cheng’s innovative fusion of knowledge distillation and modern sequence models marks him as a promising voice in autonomous systems and human motion understanding. His research holds significant implications for safer autonomous navigation and more reliable human-robot interaction.