Zobrazeno 1 - 10
of 1 522
pro vyhledávání: '"Du, Yuan"'
Multi-stage amplifiers are widely applied in analog circuits. However, their large number of components, complex transfer functions, and intricate pole-zero distributions necessitate extensive manpower for derivation and param sizing to ensure their
Externí odkaz:
http://arxiv.org/abs/2409.14739
Large language models (LLMs) excel in language tasks, especially with supervised fine-tuning after pre-training. However, their substantial memory and computational requirements hinder practical applications. Structural pruning, which reduces less si
Externí odkaz:
http://arxiv.org/abs/2408.14721
Fast convolution algorithms, including Winograd and FFT, can efficiently accelerate convolution operations in deep models. However, these algorithms depend on high-precision arithmetic to maintain inference accuracy, which conflicts with the model qu
Externí odkaz:
http://arxiv.org/abs/2407.02913
Autor:
Yang, Huanrui, Huang, Yafeng, Dong, Zhen, Gudovskiy, Denis A, Okuno, Tomoyuki, Nakata, Yohei, Du, Yuan, Keutzer, Kurt, Zhang, Shanghang
The impact of quantization on the overall performance of deep learning models is a well-studied problem. However, understanding and mitigating its effects on a more fine-grained level is still lacking, especially for harder tasks such as object detec
Externí odkaz:
http://arxiv.org/abs/2407.03442
Autor:
Zhang, Rongyu, Cheng, Aosong, Luo, Yulin, Dai, Gaole, Yang, Huanrui, Liu, Jiaming, Xu, Ran, Du, Li, Du, Yuan, Jiang, Yanbing, Zhang, Shanghang
Continual Test-Time Adaptation (CTTA), which aims to adapt the pre-trained model to ever-evolving target domains, emerges as an important task for vision models. As current vision models appear to be heavily biased towards texture, continuously adapt
Externí odkaz:
http://arxiv.org/abs/2405.16486
Autor:
Liu, Yijiang, Zhang, Rongyu, Yang, Huanrui, Keutzer, Kurt, Du, Yuan, Du, Li, Zhang, Shanghang
Large Language Models (LLMs) have demonstrated significant potential in performing multiple tasks in multimedia applications, ranging from content generation to interactive entertainment, and artistic creation. However, the diversity of downstream ta
Externí odkaz:
http://arxiv.org/abs/2404.08985
Autor:
Zhang, Ping, Lyu, Yang-Yang, Lv, Jingjing, Wei, Zihan, Chen, Shixian, Wang, Chenguang, Du, Hongmei, Li, Dingding, Wang, Zixi, Hou, Shoucheng, Su, Runfeng, Sun, Hancong, Du, Yuan, Du, Li, Gao, Liming, Wang, Yong-Lei, Wang, Huabing, Wu, Peiheng
Advanced microwave technologies constitute the foundation of a wide range of modern sciences, including quantum computing, microwave photonics, spintronics, etc. To facilitate the design of chip-based microwave devices, there is an increasing demand
Externí odkaz:
http://arxiv.org/abs/2401.12545
Autor:
Zhang, Rongyu, Cai, Zefan, Yang, Huanrui, Liu, Zidong, Gudovskiy, Denis, Okuno, Tomoyuki, Nakata, Yohei, Keutzer, Kurt, Chang, Baobao, Du, Yuan, Du, Li, Zhang, Shanghang
Finetuning a pretrained vision model (PVM) is a common technique for learning downstream vision tasks. However, the conventional finetuning process with randomly sampled data points results in diminished training efficiency. To address this drawback,
Externí odkaz:
http://arxiv.org/abs/2401.07853
Autor:
Zhang, Rongyu, Luo, Yulin, Liu, Jiaming, Yang, Huanrui, Dong, Zhen, Gudovskiy, Denis, Okuno, Tomoyuki, Nakata, Yohei, Keutzer, Kurt, Du, Yuan, Zhang, Shanghang
The Mixture-of-Experts (MoE) approach has demonstrated outstanding scalability in multi-task learning including low-level upstream tasks such as concurrent removal of multiple adverse weather effects. However, the conventional MoE architecture with p
Externí odkaz:
http://arxiv.org/abs/2312.16610
Autor:
Zhang, Yifan, Dong, Zhen, Yang, Huanrui, Lu, Ming, Tseng, Cheng-Ching, Du, Yuan, Keutzer, Kurt, Du, Li, Zhang, Shanghang
Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements. However, the huge memory consumption of state-of-the-art models makes it hard to deploy them on vehicles, and the non-trivial latency will affect the
Externí odkaz:
http://arxiv.org/abs/2308.10515