AutoGen 探索:串接常見的 LLM 模型與自建 API 伺服器AutoGen 是一個新的 AI 互動框架,透過使用者事先定義出不同 AI 助理,讓他們互動去完成最終任務,未來使用者只需要給定一個命令,AI 助理就會像是公司的職員一樣各司其職互相合作來完成任務,這些 AI…Feb 11Feb 11
An Introduction to the Foundational Model of Image Segmentation — Segment Anything (SAM)Kirillov et al., “Segment Anything, ” In Arxiv Preprint.Apr 21, 2023Apr 21, 2023
影像分割的 Foundational Model 簡介 — Segment Anything(SAM)Kirillov et al., “Segment Anything, ” In Arxiv Preprint.Apr 21, 2023Apr 21, 2023
大規模言語モデル(LLM)のファインチューニング技術「LoRA」と生成型AI「Stable diffusion LoRA」Hu et al., “LoRA: Low-Rank Adaptation of Large Language Models, ” In ICLR 2021.Mar 11, 2023Mar 11, 2023
Fine-tuning LLMs Made Easy with LoRA and Generative AI-Stable Diffusion LoRAHu et al., “LoRA: Low-Rank Adaptation of Large Language Models, ” In ICLR 2021.Mar 11, 20231Mar 11, 20231
微調大型語言模型LLM的技術LoRA及生成式AI-Stable diffusion LoRAHu et al., “LoRA: Low-Rank Adaptation of Large Language Models, ” In ICLR 2021.Mar 11, 2023Mar 11, 2023
PixMatch簡介 — Unsupervised Domain Adaptation via Pixelwise Consistency TrainingLuke Melas-Kyriazi, Arjun K. Manrai. “PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training”. In CVPR 2021.Jul 4, 2021Jul 4, 2021
Pixel2style2pixel(psp)簡介 — Encoding in Style a StyleGAN Encoder for Image-to-Image TranslationElad Richardson, Yuval Alaluf, Or Patashnik, Yotam Nitzan, Yaniv Azar, Stav Shapiro, Daniel Cohen-Or. “Encoding in Style: a StyleGAN…Jun 23, 2021Jun 23, 2021
YolactEdge簡介 — Real-time Instance Segmentation on the EdgeHaotian Liu, Rafael A. Rivera Soto, Fanyi Xiao, Yong Jae Lee. YolactEdge: Real-time Instance Segmentation on the Edge. In ArXiv preprint.Apr 13, 2021Apr 13, 2021