DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs

Item #:

079017-0739

Details

DOI: https://doi.org/10.52202/079017-0739
Author(s): Xiyang Dai, Jianfeng Gao, Yu-Gang Jiang, Lingchen Meng, Rui Tian, Zuxuan Wu, Jianwei Yang
Pages: 23464-23487 (24 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-0739
Author(s): Xiyang Dai, Jianfeng Gao, Yu-Gang Jiang, Lingchen Meng, Rui Tian, Zuxuan Wu, Jianwei Yang
Pages: 23464-23487 (24 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)