no code implementations • 17 Feb 2024 • Yixin Yang, Zheng Li, Qingxiu Dong, Heming Xia, Zhifang Sui
Understanding the deep semantics of images is essential in the era dominated by social media.
1 code implementation • 15 Jan 2024 • Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li, Zhifang Sui
To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference.
no code implementations • 24 May 2023 • Shoujie Tong, Heming Xia, Damai Dai, Runxin Xu, Tianyu Liu, Binghuai Lin, Yunbo Cao, Zhifang Sui
Also, Bi-Drop needs only one mini-batch to estimate the sub-net so it achieves higher utility of training data.
1 code implementation • 24 May 2023 • Heming Xia, Qingxiu Dong, Lei LI, Jingjing Xu, Tianyu Liu, Ziwei Qin, Zhifang Sui
Recently, Large Language Models (LLMs) have been serving as general-purpose interfaces, posing a significant demand for comprehensive visual knowledge.
1 code implementation • 8 May 2023 • Heming Xia, Peiyi Wang, Tianyu Liu, Binghuai Lin, Yunbo Cao, Zhifang Sui
In this work, we point out that there exist two typical biases after training of this vanilla strategy: classifier bias and representation bias, which causes the previous knowledge that the model learned to be shaded.
2 code implementations • 20 May 2022 • Tao Ge, Heming Xia, Xin Sun, Si-Qing Chen, Furu Wei
We study lossless acceleration for seq2seq generation with a novel decoding algorithm -- Aggressive Decoding.
Abstractive Text Summarization Grammatical Error Correction +4
2 code implementations • 30 Mar 2022 • Heming Xia, Tao Ge, Peiyi Wang, Si-Qing Chen, Furu Wei, Zhifang Sui
We propose Speculative Decoding (SpecDec), for the first time ever, to formally study exploiting the idea of speculative execution to accelerate autoregressive (AR) decoding.
no code implementations • ACL 2022 • Qingxiu Dong, Ziwei Qin, Heming Xia, Tian Feng, Shoujie Tong, Haoran Meng, Lin Xu, Weidong Zhan, Sujian Li, Zhongyu Wei, Tianyu Liu, Zuifang Sui
It is a common practice for recent works in vision language cross-modal reasoning to adopt a binary or multi-choice classification formulation taking as input a set of source image(s) and textual query.
1 code implementation • 9 Nov 2020 • Heming Xia, Lijing Shao, Junjie Zhao, Zhoujian Cao
We point out that CNN models are robust to the variation of the parameter range of the GW waveform.