Qianli Ma

7

Papers

229

Total Citations

Papers (7)

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

Diffusion Language-Shapelets for Semi-supervised Time-Series Classification

Articulated Kinematics Distillation from Video Diffusion Models

Degrees of Freedom Matter: Inferring Dynamics from Point Trajectories

Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

Efficient Diffusion as Low Light Enhancer