Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Gong, Ruihao"'
Autor:
Yao, Yongqiang, Tan, Jingru, Hu, Jiahao, Zhang, Feizhao, Jin, Xin, Li, Bo, Gong, Ruihao, Liu, Pengfei
Recently, vision-language instruct-tuning models have made significant progress due to their more comprehensive understanding of the world. In this work, we discovered that large-scale 3D parallel training on those models leads to an imbalanced compu
Externí odkaz:
http://arxiv.org/abs/2407.20761
The Diffusion models, widely used for image generation, face significant challenges related to their broad applicability due to prolonged inference times and high memory demands. Efficient Post-Training Quantization (PTQ) is crucial to address these
Externí odkaz:
http://arxiv.org/abs/2407.19547
The typical process for developing LLMs involves pre-training a general foundation model on massive data, followed by fine-tuning on task-specific data to create specialized experts. Serving these experts poses challenges, as loading all experts onto
Externí odkaz:
http://arxiv.org/abs/2406.09041
Autor:
Fan, Yunqian, Wei, Xiuying, Gong, Ruihao, Ma, Yuqing, Zhang, Xiangguo, Zhang, Qi, Liu, Xianglong
Publikováno v:
AAAI 2024, 38, 11936-11943
Lane detection (LD) plays a crucial role in enhancing the L2+ capabilities of autonomous driving, capturing widespread attention. The Post-Processing Quantization (PTQ) could facilitate the practical application of LD models, enabling fast speeds and
Externí odkaz:
http://arxiv.org/abs/2405.06264
Autor:
Gong, Ruihao, Yong, Yang, Wang, Zining, Guo, Jinyang, Wei, Xiuying, Ma, Yuqing, Liu, Xianglong
Neural network sparsity has attracted many research interests due to its similarity to biological schemes and high energy efficiency. However, existing methods depend on long-time training or fine-tuning, which prevents large-scale applications. Rece
Externí odkaz:
http://arxiv.org/abs/2405.05808
Autor:
Gong, Ruihao, Yong, Yang, Gu, Shiqiao, Huang, Yushi, Lv, Chentao, Zhang, Yunchen, Liu, Xianglong, Tao, Dacheng
Recent advancements in large language models (LLMs) are propelling us toward artificial general intelligence with their remarkable emergent abilities and reasoning capabilities. However, the substantial computational and memory requirements limit the
Externí odkaz:
http://arxiv.org/abs/2405.06001
Autor:
Chen, Leo, Boardley, Benjamin, Hu, Ping, Wang, Yiru, Pu, Yifan, Jin, Xin, Yao, Yongqiang, Gong, Ruihao, Li, Bo, Huang, Gao, Liu, Xianglong, Wan, Zifu, Chen, Xinwang, Liu, Ning, Zhang, Ziyi, Liu, Dongping, Shan, Ruijie, Che, Zhengping, Zhang, Fachao, Mou, Xiaofeng, Tang, Jian, Chuprov, Maxim, Malofeev, Ivan, Goncharenko, Alexander, Shcherbin, Andrey, Yanchenko, Arseny, Alyamkin, Sergey, Hu, Xiao, Thiruvathukal, George K., Lu, Yung Hsiang
This article describes the 2023 IEEE Low-Power Computer Vision Challenge (LPCVC). Since 2015, LPCVC has been an international competition devoted to tackling the challenge of computer vision (CV) on edge devices. Most CV researchers focus on improvin
Externí odkaz:
http://arxiv.org/abs/2403.07153
Recent advancements in generative large language models (LLMs) have significantly boosted the performance in natural language processing tasks. However, their efficiency is hampered by the inherent limitations in autoregressive token generation. Whil
Externí odkaz:
http://arxiv.org/abs/2402.13485
The Diffusion model, a prevalent framework for image generation, encounters significant challenges in terms of broad applicability due to its extended inference times and substantial memory requirements. Efficient Post-training Quantization (PTQ) is
Externí odkaz:
http://arxiv.org/abs/2311.16503
Autor:
Zhang, Zhuoyi, Zhang, Yunchen, Shi, Gonglei, Shen, Yu, Gong, Ruihao, Xia, Xiaoxu, Zhang, Qi, Lu, Lewei, Liu, Xianglong
Neural network quantization is widely used to reduce model inference complexity in real-world deployments. However, traditional integer quantization suffers from accuracy degradation when adapting to various dynamic ranges. Recent research has focuse
Externí odkaz:
http://arxiv.org/abs/2310.13513