Xinyin Ma
11
Papers
424
Total Citations
Papers (11)
DeepCache: Accelerating Diffusion Models for Free
CVPR 2024arXiv
265
citations
dKV-Cache: The Cache for Diffusion Language Models
NeurIPS 2025arXiv
66
citations
Thinkless: LLM Learns When to Think
NeurIPS 2025arXiv
58
citations
Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
CVPR 2025arXiv
19
citations
VeriThinker: Learning to Verify Makes Reasoning Model Efficient
NeurIPS 2025arXiv
16
citations
TinyFusion: Diffusion Transformers Learned Shallow
CVPR 2025arXiv
0
citations
Diffusion Model is Effectively Its Own Teacher
CVPR 2025
0
citations
Auto-Controlled Image Perception in MLLMs via Visual Perception Tokens
ICCV 2025
0
citations
DepGraph: Towards Any Structural Pruning
CVPR 2023arXiv
0
citations
Structural Pruning for Diffusion Models
NeurIPS 2023arXiv
0
citations
LLM-Pruner: On the Structural Pruning of Large Language Models
NeurIPS 2023arXiv
0
citations