Jian Jun Zhang

MoFA: Dual-Task Motion Factorization for Human Motion Synthesis with Imperfect and Limited Data

Zero-Shot Cross-Domain Dialogue State Tracking with Small LLMs: Learning to Think through Reinforcement Learning

Learning Vortex Enhancement with Angular-Speed-Invariant Importance Sampling in SPH Fluids

PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding