Kaisheng Ma

20

Papers

456

Total Citations

Papers (20)

DreamLLM: Synergistic Multimodal Comprehension and Creation

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

NeurIPS 2025arXiv

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices

CutFreq: Cut-and-Swap Frequency Components for Low-Level Vision Augmentation

Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation

Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance With Expanded Views

Adversarial Robustness vs. Model Compression, or Both?

Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation

Tiny Updater: Towards Efficient Neural Network-Driven Software Updating

Contrastive Deep Supervision

PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection

MindPainter: Efficient Brain-Conditioned Painting of Natural Images via Cross-Modal Self-Supervised Learning

Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation

Auxiliary Training: Towards Accurate and Robust Models

Light-weight Calibrator: A Separable Component for Unsupervised Domain Adaptation

SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models

Task-Oriented Feature Distillation

AFEC: Active Forgetting of Negative Transfer in Continual Learning

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation