Ping Luo (羅平) (original) (raw)
GenTron: Diffusion Transformers for Image and Video Generation
CVPR'24 Project
MotionCtrl: A Unified and Flexible Motion Controller for Video Generation
VDT: General-purpose Video Diffusion Transformers via Mask Modeling
ICLR'24
PIXART-α:Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
ICLR'24 Spotlight Project
PIXART-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
ICLR'24 Spotlight Project and Code
RegionGPT: Towards Region Understanding Vision Language Model
CVPR'24 paper
RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
FlashFace: Human Image Personalization with High-fidelity Identity Preservation
Biography
- colorgreenmathcalNew!\color{green}{\mathcal{N}ew!}colorgreenmathcalNew! We’re actively recruiting Postdocs, PhDs, and RAs. Please drop me an email via pluo.lhi@gmail.com.
- 2024-03: Two papers will be presented in SIGGRAPH'24, eight papers in ICLR'24 (two spotlights), eight papers in CVPR'24.
- 2024-01: Received the prestigious HKU Outstanding Young Researcher Award 2023. Enjoy the video!
- 2023-10: DiffusionDet was nominated for the Best Paper Final List (17/8260, 0.2%) at ICCV 2023. PVT v2 received the Best Paper Runner-up of the Year 2023 at the Computaional Visual Media Journal (CVMJ). SegFormer and PVT v1 received the Outstanding Young Paper Awards at the World AI Conference (WAIC) 2023.
- 2023-06: Ten papers will be presented in CVPR'23, eleven in ICCV'23, three in ICLR'23, three in ICML'23, six in NeurIPS'23.
- 2022-05: Our paper “Compression of Generative Pre-trained Language Models via Quantization” received ACL 2022 Outstanding Paper Award. 5 papers were presented in ICLR 2022 (CycleMLP is an oral presentation, accepted rate 1.6%), 7 papers in CVPR 2022 (2 oral presentation), 3 papers will be presented in ICML 2022.
My researches aim at (1) developing Differentiable/ Meta/ Reinforcement Learning algorithms that endow machines and devices to solve complex tasks with larger autonomy, (2) understanding foundations of deep learning algorithms, and (3) enabling applications in Machine Vision and Artificial Intelligence such as text to image/video generation, 3D vision, scene and video understanding, and medical image analysis.
Biography Ping Luo is an Associate Professor in the Department of Computer Science at the University of Hong Kong, an Associate Director of the HKU Musketeers Foundation Institute of Data Science (HKU IDS), and a Deputy Director of the Joint Research Lab of HKU and Shanghai AI Lab. He obtained his Ph.D. in Information Engineering from the Chinese University of Hong Kong in 2014, under the supervision of Prof. Xiaoou Tang (founder of SenseTime) and Prof. Xiaogang Wang. Before joining HKU in 2019, he was a Research Director in SenseTime. He has published 100+ papers in international conferences and journals such as TPAMI, ICML, ICLR, NeurIPS, and CVPR, with over 50,000 citations on Google Scholar. He was awarded the 2015 AAAI Easily Accessible Paper, nominated for the 2022 Computational Visual Media Journal's Best Paper of the Year, won the 2022 ACL Outstanding Paper, the 2023 World Artificial Intelligence Conference (WAIC) Outstanding Papers, and was a candidate for the Best Paper at ICCV’23. He was recognized as one of the innovators under 35 in the Asia-Pacific region by the MIT Technology Review (MIT TR35) in 2020. He has mentored 30 Ph.D. students, many of whom have received significant awards such as the Nvidia Fellowship, Baidu Fellowship, WAIC Yunfan Award, etc.
Recent Publications
Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, Jifeng Dai (2023).Visionllm: Large language model is also an open-ended decoder for vision-centric tasks.Thirty-seventh Annual Conference on Neural Information Processing Systems (NeurIPS) 2023.
News&Talks
Principal Investigator
Advisory Committee
PhD Candidates
Chongjian GE
PhD, since 2020 (HKPFS). webpage
Object Detection, Visual Question Answering, Deep Learning
Fanqing Meng
PhD, 2023-, Shanghai AI Lab Joint PhD Program
Text-to-Image, LLM
Haibao Yu
PhD, since 2022. webpage
V2X, Autonomous Driving, Computer Vision, Efficient AI
Jiannan Wu
PhD, since 2020 (HKPFS). webpage
Math Exercise Representation, Visual Question Answering, Deep Learning
Peng Xu
PhD, since 2021 (HKU-SUSTech Joint PhD Programme). Co-supervised with Prof. Fengwei An
Computer Vision, Edge Computing
Runjian Chen
PhD, since 2021 (HKPFS). webpage
Representation Learning, Deep Learning, Autonomous Driving, 3D Computer Vision
Teng Wang
PhD, since 2020 (HKU-SUSTech Joint PhD Programme). Co-supervised with Prof. Feng Zheng
Neural Architecture Search, Deep Learning
Yao Lai
PhD, since 2021 (HKPFS). webpage
AI Security, Electronic Design Automation, High Performance Computing
Yao Mu
PhD, since 2021 (HKPFS). webpage
Unsupervised Representation Learning, Reinforcement Learning
Yizhuo Li
PhD, since 2022. webpage
Video Understanding, Self-supervised Learning
Yue Yang
PhD, 2022-, Shanghai AI Lab Joint PhD Program
Text-to-Image, LLM
Yuheng Lei
PhD (HKPFS), 2023-, webpage
Embodied AI, Reinforcement Learning, Robotics, Autonomous Driving
Zeyue Xue
PhD, since 2022.
Large-scale Deep Learning, Computer Vision
Zhixuan Liang
PhD, since 2022 (HKPFS). webpage
Active Learning and Incremental Learning, Open World Detection, Autonomous Driving
Alumni
Enze Xie
PhD, 2019-2022. webpage
Instance-level Detection and Segmentation, Text Understanding, Deep Learning
Wenhai Wang
RA, 2019-2020. webpage
Text Understanding, Instance-level Detection and Segmentation, Deep Learning
Yangyang Xu
Postdoc Fellow, 2021-2023. webpage
Generative Models, Image Editing, Transfer Learning
Yutao Hu
Postdoc Fellow, 2022-2023. webpage
AI for Healthcare, Computer Vision
Zhouxia Wang
PhD, 2020-2023. webpage Co-supervised with Prof. Wenping Wang
Exposure Bracketing Selection, Multi-exposure Fusion and Image Denoising, Image Recognition and Object Detection, Deep Learning
Projects
*
DeepFashion2
DeepFashion second edition with a full-spectrum of fashion image analyses.
CUImage Dataset
A large-scale dataset for learning general visual representation.
WIDERFace
A large-scale dense face detection challenge.
CelebA
Face celebrity dataset for attribute recognition and GANs.