Zobrazeno 1 - 10
of 6 955
pro vyhledávání: '"Han, Song"'
As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed decreases
Externí odkaz:
http://arxiv.org/abs/2406.10774
Autor:
Ye, Hanrong, Huang, De-An, Lu, Yao, Yu, Zhiding, Ping, Wei, Tao, Andrew, Kautz, Jan, Han, Song, Xu, Dan, Molchanov, Pavlo, Yin, Hongxu
We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion decoders with LL
Externí odkaz:
http://arxiv.org/abs/2405.19335
Autor:
Lin, Yujun, Tang, Haotian, Yang, Shang, Zhang, Zhekai, Xiao, Guangxuan, Gan, Chuang, Han, Song
Quantization can accelerate large language model (LLM) inference. Going beyond INT8 quantization, the research community is actively exploring even lower precision, such as INT4. Nonetheless, state-of-the-art INT4 quantization techniques only acceler
Externí odkaz:
http://arxiv.org/abs/2405.04532
Industrial Internet of Things (IIoT) technologies have revolutionized industrial processes, enabling smart automation, real-time data analytics, and improved operational efficiency across diverse industry sectors. IIoT testbeds play a critical role i
Externí odkaz:
http://arxiv.org/abs/2404.17485
We present Condition-Aware Neural Network (CAN), a new method for adding control to image generative models. In parallel to prior conditional control methods, CAN controls the image generation process by dynamically manipulating the weight of the neu
Externí odkaz:
http://arxiv.org/abs/2404.01143
Publikováno v:
IEEE Circuits and Systems Magazine, 23(3), pp. 8-34, October 2023
Tiny Machine Learning (TinyML) is a new frontier of machine learning. By squeezing deep learning models into billions of IoT devices and microcontrollers (MCUs), we expand the scope of AI applications and enable ubiquitous intelligence. However, Tiny
Externí odkaz:
http://arxiv.org/abs/2403.19076
Autor:
Li, Muyang, Cai, Tianle, Cao, Jiaxin, Zhang, Qinsheng, Cai, Han, Bai, Junjie, Jia, Yangqing, Liu, Ming-Yu, Li, Kai, Han, Song
Diffusion models have achieved great success in synthesizing high-quality images. However, generating high-resolution images with diffusion models is still challenging due to the enormous computational costs, resulting in a prohibitive latency for in
Externí odkaz:
http://arxiv.org/abs/2402.19481
Large Language Models (LLMs) are typically trained in two phases: pre-training on large internet-scale datasets, and fine-tuning for downstream tasks. Given the higher computational demand of pre-training, it's intuitive to assume that fine-tuning ad
Externí odkaz:
http://arxiv.org/abs/2402.10193
We present EfficientViT-SAM, a new family of accelerated segment anything models. We retain SAM's lightweight prompt encoder and mask decoder while replacing the heavy image encoder with EfficientViT. For the training, we begin with the knowledge dis
Externí odkaz:
http://arxiv.org/abs/2402.05008
Autor:
Zhang, Junyao, Wang, Hanrui, Ding, Qi, Gu, Jiaqi, Assouly, Reouven, Oliver, William D., Han, Song, Brown, Kenneth R., Li, Hai "Helen", Chen, Yiran
Noisy Intermediate-Scale Quantum (NISQ) computers face a critical limitation in qubit numbers, hindering their progression towards large-scale and fault-tolerant quantum computing. A significant challenge impeding scaling is crosstalk, characterized
Externí odkaz:
http://arxiv.org/abs/2401.17450