3 citations · 3 across the 4 of their papers we have counts for
4 papers
DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs
Zhenhailong Wang, Senthil Purushwalkam, Caiming Xiong +3
We present DyMU, an efficient, training-free framework that dynamically reduces the computational burden of vision-language models (VLMs) while maintaining high task performance. O…
Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models
Yuheng Wu, Wentao Guo, Zirui Liu +3
This paper investigates the emergence of Theory-of-Mind (ToM) capabilities in large language models (LLMs) from a mechanistic perspective, focusing on the role of extremely sparse…
Fact Checking Beyond Training Set
Payam Karisani, Heng Ji
Evaluating the veracity of everyday claims is time consuming and in some cases requires domain expertise. We empirically demonstrate that the commonly used fact checking pipeline,…
Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking
Yi Fung, Ruining Zhao, Jae Doo +2
Pretrained large language models have revolutionized many applications but still face challenges related to cultural bias and a lack of cultural commonsense knowledge crucial for g…