Changxing Ding

ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning

High-Fidelity Human Motion Generation with Motion Quality Feedbacks

Reconstruction for Generation: Regularizing Motion Diffusion Models with Motion Reconstruction

Test-Real-Time Adaptation against Sparse Knowledge Bottleneck

Partition-Then-Adapt: Combating Prediction Bias for Reliable Multi-Modal Test-Time Adaptation

Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation

Multi-modal Controlled Coherent Motion Synthesis

Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models