Joey Tianyi Zhou

SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodal LLMs featured image
Featured

SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodal LLMs

*Advances in Neural Information Processing Systems (NeurIPS)*, 2025

jinhong-deng
•
Read more
Multisize Dataset Condensation featured image
Source Themes

Multisize Dataset Condensation

*International Conference on Learning Representations (ICLR) Oral*, 2024

avatar
Yang He
•
Read more
Data-independent Module-aware Pruning for Hierarchical Vision Transformers featured image
Source Themes

Data-independent Module-aware Pruning for Hierarchical Vision Transformers

*International Conference on Learning Representations (ICLR)*, 2024

avatar
Yang He
•
Read more
You Only Condense Once: Two Rules for Pruning Condensed Datasets featured image
Source Themes

You Only Condense Once: Two Rules for Pruning Condensed Datasets

*Advances in Neural Information Processing Systems (NeurIPS)*, 2023

avatar
Yang He
•
Read more