Xinzhu Ma

7

Papers

60

Total Citations

Papers (7)

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers

Revisiting Convolution Architecture in the Realm of DNA Foundation Models

CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation

Retraining-Free Model Quantization via One-Shot Weight-Coupling Learning

RobAVA: A Large-scale Dataset and Baseline Towards Video based Robotic Arm Action Understanding

UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines

Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts