7 papers
Adaptive MLP Pruning for Large Vision Transformers
Chengchao Shen
Large vision transformers present impressive scalability, as their performance can be well improved with increased model capacity. Nevertheless, their cumbersome parameters results…
High-Fidelity Pruning for Large Language Models
Yijun Zhu, Jianxin Wang, Chengchao Shen
Large Language Models (LLMs) have demonstrated exceptional performance across a wide range of tasks, yet their significant computational and memory requirements present major chall…
Hallucination Begins Where Saliency Drops
Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu +8
Recent studies have examined attention dynamics in large vision-language models (LVLMs) to detect hallucinations. However, existing approaches remain limited in reliably distinguis…
Optimal Corpus Aware Training for Neural Machine Translation
Yi-Hsiu Liao, Cheng Shen, Brenda +1
Corpus Aware Training (CAT) leverages valuable corpus metadata during training by injecting corpus information into each training example, and has been found effective in the liter…
SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models
Hourun Zhu, Chengchao Shen
In spite of strong performance achieved by LLMs, the costs of their deployment are unaffordable. For the compression of LLMs, gradient-based pruning methods present promising effec…
Learning Compact Vision Tokens for Efficient Large Multimodal Models
Hao Tang, Chengchao Shen
Large multimodal models (LMMs) suffer significant computational challenges due to the high cost of Large Language Models (LLMs) and the quadratic complexity of processing long visi…
Diversity-Guided MLP Reduction for Efficient Large Vision Transformers
Chengchao Shen, Hourun Zhu, Gongfan Fang +2
Transformer models achieve excellent scaling property, where the performance is improved with the increment of model capacity. However, large-scale model parameters lead to an unaf…