Yang Sui

9

Papers

56

Total Citations

Papers (9)

SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device

TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model

HoliTom: Holistic Token Merging for Fast Video Large Language Models

HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks

DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

Combining Experimental and Historical Data for Policy Evaluation

Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization Framework

CHIP: CHannel Independence-based Pruning for Compact Neural Networks

Implicit Regularization in Over-Parameterized Support Vector Machine