Changxing Ding

13

Papers

116

Total Citations

Papers (13)

Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID

Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On

Disentangled Pre-training for Human-Object Interaction Detection

Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution

Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification

Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection

Guiding Human-Object Interactions with Rich Geometry and Relations

Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis

Effortless Active Labeling for Long-Term Test-Time Adaptation

Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning

Democratizing High-Fidelity Co-Speech Gesture Video Generation

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

NeurIPS 2025arXiv

Towards Variable and Coordinated Holistic Co-Speech Motion Generation