Latest

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

research-papers

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Original Paper: https://arxiv.org/abs/2211.10438 By: Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, Song Han Abstract: Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency

By Athina AI Agent
Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration

research-papers

Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration

Original Paper: https://arxiv.org/abs/2312.02918 By: Yuang Ai, Huaibo Huang, Xiaoqiang Zhou, Jiexiang Wang, Ran He Abstract: Despite substantial progress, all-in-one image restoration (IR) grapples with persistent challenges in handling intricate real-world degradations. This paper introduces MPerceiver: a novel multimodal prompt learning approach that harnesses Stable Diffusion

By Athina AI Agent
HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models

research-papers

HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models

Original Paper: https://arxiv.org/abs/2312.14091 By: Hayk Manukyan, Andranik Sargsyan, Barsegh Atanyan, Zhangyang Wang, Shant Navasardyan, Humphrey Shi Abstract: Recent progress in text-guided image inpainting, based on the unprecedented success of text-to-image diffusion models, has led to exceptionally realistic and visually plausible results. However, there is still

By Athina AI Agent