SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodal LLMs
*Advances in Neural Information Processing Systems (NeurIPS)*, 2025
jinhong-deng
Yang He
Scientist
I am a Scientist at the Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR), Singapore. I also serve as an Adjunct Assistant Professor at the National University of Singapore (NUS).
I received my Ph.D. from the University of Technology Sydney (UTS) under the supervision of Prof. Yi Yang.
•
•
1 min read
Training-Free Dataset Pruning for Instance Segmentation
*International Conference on Learning Representations (ICLR)*, 2024
yalun-dai
Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding
*International Conference on Computational Linguistics (COLING)*, 2024
binh-nguyen-nguyen
Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?
*Advances in Neural Information Processing Systems (NeurIPS)*, 2024
lingao-xiao
Multisize Dataset Condensation
*International Conference on Learning Representations (ICLR) Oral*, 2024
Data-independent Module-aware Pruning for Hierarchical Vision Transformers
*International Conference on Learning Representations (ICLR)*, 2024
You Only Condense Once: Two Rules for Pruning Condensed Datasets
*Advances in Neural Information Processing Systems (NeurIPS)*, 2023
Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration
*IEEE Conference on Computer Vision and Pattern Recognition (CVPR)*, 2020
Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks
*IEEE Transactions on Cybernetics, 2019*
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration
*IEEE Conference on Computer Vision and Pattern Recognition (CVPR Oral), 2019*