Výsledky vyhledávání - "Meng, Hengyu"

Report

DEGAS: Detailed Expressions on Full-Body Gaussian Avatars

Autor: Shao, Zhijing, Wang, Duotun, Tian, Qing-Yao, Yang, Yao-Dong, Meng, Hengyu, Cai, Zeyu, Dong, Bo, Zhang, Yu, Zhang, Kang, Wang, Zeyu

Although neural rendering has made significant advancements in creating lifelike, animatable full-body and head avatars, incorporating detailed expressions into full-body avatars remains largely unexplored. We present DEGAS, the first 3D Gaussian Spl

Externí odkaz: http://arxiv.org/abs/2408.10588

Zobrazit plný text záznamu

Report

HeadEvolver: Text to Head Avatars via Expressive and Attribute-Preserving Mesh Deformation

Autor: Wang, Duotun, Meng, Hengyu, Cai, Zeyu, Shao, Zhijing, Liu, Qianxi, Wang, Lin, Fan, Mingming, Zhan, Xiaohang, Wang, Zeyu

Current text-to-avatar methods often rely on implicit representations (e.g., NeRF, SDF, and DMTet), leading to 3D content that artists cannot easily edit and animate in graphics software. This paper introduces a novel framework for generating stylize

Externí odkaz: http://arxiv.org/abs/2403.09326

Zobrazit plný text záznamu

Report

MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising

Autor: Wang, Bingyuan, Meng, Hengyu, Cai, Zeyu, Li, Lanjiong, Ma, Yue, Chen, Qifeng, Wang, Zeyu

Visual storytelling often uses nontypical aspect-ratio images like scroll paintings, comic strips, and panoramas to create an expressive and compelling narrative. While generative AI has achieved great success and shown the potential to reshape the c

Externí odkaz: http://arxiv.org/abs/2312.10899

Zobrazit plný text záznamu

Report

Efficient LLM Inference on CPUs

Autor: Shen, Haihao, Chang, Hanwen, Dong, Bo, Luo, Yu, Meng, Hengyu

Large language models (LLMs) have demonstrated remarkable performance and tremendous potential across a wide range of tasks. However, deploying these models has been challenging due to the astronomical amount of model parameters, which requires a dem

Externí odkaz: http://arxiv.org/abs/2311.00502

Zobrazit plný text záznamu

Report

An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs

Autor: Shen, Haihao, Meng, Hengyu, Dong, Bo, Wang, Zhe, Zafrir, Ofir, Ding, Yi, Luo, Yu, Chang, Hanwen, Gao, Qun, Wang, Ziheng, Boudoukh, Guy, Wasserblat, Moshe

In recent years, Transformer-based language models have become the standard approach for natural language processing tasks. However, stringent throughput and latency requirements in industrial applications are limiting their adoption. To mitigate the

Externí odkaz: http://arxiv.org/abs/2306.16601

Zobrazit plný text záznamu

Report

Fast DistilBERT on CPUs

Autor: Shen, Haihao, Zafrir, Ofir, Dong, Bo, Meng, Hengyu, Ye, Xinyu, Wang, Zhe, Ding, Yi, Chang, Hanwen, Boudoukh, Guy, Wasserblat, Moshe

Transformer-based language models have become the standard approach to solving natural language processing tasks. However, industry adoption usually requires the maximum throughput to comply with certain latency constraints that prevents Transformer

Externí odkaz: http://arxiv.org/abs/2211.07715

Zobrazit plný text záznamu