Bin Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bin Gao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Fan Wu
Shanghai Jiao Tong University, Shanghai, China
2 shared publications - Pengfei Zuo
The Chinese University of Hong Kong The Chinese University of Hong Kong The Chinese University of Hong Kong
2 shared publications - Qinya Li
Shanghai Jiao Tong University, Shanghai, China
2 shared publications Yizhen Yao
Shanghai Jiao Tong University
2 shared publications- Zhenzhe Zheng
Shanghai Jiao Tong University, Shanghai, China
2 shared publications Zhuomin He
Shanghai Jiao Tong University
2 shared publications
Latest Publications
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (22) , 24050-24058
AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference. We observe that existing layer-wise skipping strategies have several limitations when applied in long-context inference, including the inability to adapt to model and context variability, disregard for sublayer significance, and inapplicability for the prefilling phase. This paper proposes AdaSkip, an adaptive sublayer skipping method specifically designed for long-context inference. AdaSkip adaptively identifies less important layers by leveraging on-the-fly similarity information, enables sublayer-wise skipping, and accelerates both the prefilling and decoding phases. The effectiveness of AdaSkip is demonstrated through extensive experiments on various long-context benchmarks and models, showcasing its superior inference performance over existing baselines.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (22) , 24050-24058
Open AccessAdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference. We observe that existing layer-wise skipping strategies have several limitations when applied in long-context inference, including the inability to adapt to model and context variability, disregard for sublayer significance, and inapplicability for the prefilling phase. This paper proposes AdaSkip, an adaptive sublayer skipping method specifically designed for long-context inference. AdaSkip adaptively identifies less important layers by leveraging on-the-fly similarity information, enables sublayer-wise skipping, and accelerates both the prefilling and decoding phases. The effectiveness of AdaSkip is demonstrated through extensive experiments on various long-context benchmarks and models, showcasing its superior inference performance over existing baselines.
- Open Access
AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference. We observe that existing layer-wise skipping strategies have several limitations when applied in long-context inference, including the inability to adapt to model and context variability, disregard for sublayer significance, and inapplicability for the prefilling phase. This paper proposes \sysname, an adaptive sublayer skipping method specifically designed for long-context inference. \sysname adaptively identifies less important layers by leveraging on-the-fly similarity information, enables sublayer-wise skipping, and accelerates both the prefilling and decoding phases. The effectiveness of \sysname is demonstrated through extensive experiments on various long-context benchmarks and models, showcasing its superior inference performance over existing baselines.
Open AccessAdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference. We observe that existing layer-wise skipping strategies have several limitations when applied in long-context inference, including the inability to adapt to model and context variability, disregard for sublayer significance, and inapplicability for the prefilling phase. This paper proposes \sysname, an adaptive sublayer skipping method specifically designed for long-context inference. \sysname adaptively identifies less important layers by leveraging on-the-fly similarity information, enables sublayer-wise skipping, and accelerates both the prefilling and decoding phases. The effectiveness of \sysname is demonstrated through extensive experiments on various long-context benchmarks and models, showcasing its superior inference performance over existing baselines.