I am Simian Luo, 23, currently a second year M.S student in Artificial Intelligence at
IIIS (Institute for Interdisciplinary Information Sciences), Tsinghua University (清华交叉信息研究院)
advised by Prof. Hang Zhao.
Previously, I received my B.E. in Data Science from School of Data Science,
Fudan University, advised by Prof. Yanwei Fu.
My research interest focus on Advanced Generative Model, Multi-Modal Generation and LLM Application.
In specfic, I have researched in diffusion model, audio-visual generation, 3D generation, and Augmentated LLM.
Currently, I am focused on developing new advanced Generative Models that can accelerate the development of the AI Generated Content (AIGC) industry.
E-Mail |
Google Scholar |
Github
|
|
Nov. 2023 |
Follow our latest work: LCM-LoRA: A Universal Stable-Diffusion Acceleration Module. A training-free neural network-based acceleration module that can directly plugged into various finetuned SD and SD LoRAs.!!
|
Oct. 2023 |
Follow our latest work: Latent Consistency Models: Synthesizing High-Resolution Images With Few-Step Inference. The next generation of generative models after latent diffusion models (LDMs) !!
|
June. 2023 |
Oral Presentation at CVPR 2023 Sight and Sound Workshop about our latest work:
Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models.
|
Publications
* indicates equal contribution
|
|
LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
Simian Luo*, Yiqin Tan*, Suraj Patil†, Daniel Gu†, Patrick von Platen, Apolinário Passos, Longbo Huang, Jian Li, Hang Zhao
(*:Leading Authors, †:Core Contributor)
Technical Report 2023.11
|
|
Latent Consistency Models: Synthesizing High-Resolution Images With Few-Step Inference
Simian Luo*, Yiqin Tan*, Longbo Huang†, Jian Li†, Hang Zhao†
Preprint 2023.10
|
|
Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models
Simian Luo, Chuanhao Yan, Chenxu Hu, Hang Zhao
NeurIPS 2023
|
|
ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
Chenxu Hu*, Jie Fu*, Chenzhuang Du, Simian Luo, Junbo Zhao, Hang Zhao
LLM @ IJCAI 2023
|
|
Learning Versatile 3D Shape Generation with Improved AR Models
Simian Luo*, Xuelin Qian*, Yanwei Fu, Yinda Zhang, Ying Tai, Zhenyu Zhang, Chengjie Wang, Xiangyang Xue
ICCV 2023
|
|
QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation
Yuxin Hong, Xuelin Qian, Simian Luo, Guoguo Guo, Xiangyang Xue, Yanwei Fu
ACCV 2022
|
June 2023 |
Invited paper talk at Sight and Sound Workshop, CVPR 2023, "Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models."
|
   
|
   
|
FDU 2018-2022 |
THU 2022 - Present |
|