Picture for Wenxuan Huang

Wenxuan Huang

Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

Add code
Dec 03, 2024
Viaarxiv icon

A General and Efficient Training for Transformer via Token Expansion

Add code
Mar 31, 2024
Figure 1 for A General and Efficient Training for Transformer via Token Expansion
Figure 2 for A General and Efficient Training for Transformer via Token Expansion
Figure 3 for A General and Efficient Training for Transformer via Token Expansion
Figure 4 for A General and Efficient Training for Transformer via Token Expansion
Viaarxiv icon

Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler

Add code
Jul 01, 2023
Figure 1 for Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
Figure 2 for Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
Figure 3 for Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
Figure 4 for Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
Viaarxiv icon

cGANs for Cartoon to Real-life Images

Add code
Jan 24, 2021
Figure 1 for cGANs for Cartoon to Real-life Images
Figure 2 for cGANs for Cartoon to Real-life Images
Figure 3 for cGANs for Cartoon to Real-life Images
Figure 4 for cGANs for Cartoon to Real-life Images
Viaarxiv icon