Picture for Hengyu Meng

Hengyu Meng

DEGAS: Detailed Expressions on Full-Body Gaussian Avatars

Add code
Aug 20, 2024
Viaarxiv icon

HeadEvolver: Text to Head Avatars via Locally Learnable Mesh Deformation

Add code
Mar 14, 2024
Viaarxiv icon

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

Add code
Dec 18, 2023
Viaarxiv icon

Efficient LLM Inference on CPUs

Add code
Nov 01, 2023
Viaarxiv icon

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

Add code
Jun 28, 2023
Viaarxiv icon

Fast DistilBERT on CPUs

Add code
Oct 27, 2022
Viaarxiv icon