Lv/Lyu Tang

My name is Lv Tang. I received my Bachelor of Science degree from the School of Information Science and Technology, Southwest Jiaotong University (SWJTU) in 2018. I obtained my Master’s degree from the Department of Computer Science, Nanjing University in 2021. I received my Ph.D. degree from the School of Computer Science and Technology, University of Chinese Academy of Sciences (UCAS) in 2025. I am currently a Postdoctoral Researcher in the Department of Electrical and Computer Engineering at the University of Alberta.

Email  /  Resume  /  Twitter  /  Google Scholar  /  Github

profile photo
Research

I received my Ph.D. degree from the University of Chinese Academy of Sciences (UCAS), where my research focused on generative AI, high-level vision and low-level vision. Looking ahead, my research interests primarily lie in MLLMs and their applications across various downstream tasks. To date, I have published 13 papers in top-tier conferences and journals, contributing to a total of 35 publications that have accumulated over 1250 citations.

News
  • 2026-05: One paper is accpeted by TIP 2026.
  • 2025-12: One paper is accpeted by TMM 2025.
  • 2025-08: One paper is accpeted by Neural Networks 2025.
  • 2024-12: Two papers are accpeted by TOMM 2024 and AAAI2025.
  • 2024-07: One paper is accpeted by ACMMM 2024.
  • 2024-06: One paper is accpeted by IJCV 2024.
  • 2024-03: One paper is accepted by TOMM 2024.
  • 2024-02: One paper is accepted by CVPR 2024.
Selected Publications
PontTuset Boosting Vision State Space Model with Fractal Scanning
Haoke Xiao, Lv Tang*, Peng-Tao Jiang, Hao Zhang, Jinwei Chen, Bo Li (Corresponding author and Co-first author)
AAAI 2025 (Oral)

PontTuset CoVP: Harnessing multimodal large language models for zero-shot camouflaged object detection
Lv Tang, Peng-Tao Jiang, Zhi-Hao Shen, Hao Zhang, Jinwei Chen, Bo Li
ACMMM 2024

PontTuset Towards training-free open-world segmentation via image prompting foundation models
Lv Tang, Peng-Tao Jiang, Haoke Xiao, Bo Li
IJCV 2024

PontTuset ASAM: boosting segment anything model with adversarial tuning
Bo Li, Haoke Xiao, Lv Tang* (Corresponding author)
CVPR 2024

PontTuset From composited to real-world: Transformer-based natural image matting
Yanfeng Wang, Lv Tang*, Yi-Jie Zhong, Bo Li (Corresponding author)
TCSVT 2024

PontTuset High Efficiency Deep-learning Based Video Compression
Lv Tang, Xinfeng Zhang
TOMM 2024

PontTuset Scene Matters: Model-based Deep Video Compression
Lv Tang, Xinfeng Zhang, Gai Zhang, Xiaoqi Ma
ICCV 2023

PontTuset Toward stable co-saliency detection and object co-segmentation
Bo Li, Lv Tang*, Senyun Kuang, Mofei Song, Shouhong Ding (Corresponding author)
TIP 2022

PontTuset Re-thinking the relations in co-saliency detection
Lv Tang, Bo Li, Senyun Kuang, Mofei Song, Shouhong Ding
TCSVT 2022

PontTuset Detecting camouflaged object in frequency domain
Yi-Jie Zhong, Bo Li, Lv Tang*#, Senyun Kuang, Shuang Wu, Shouhong Ding (Corresponding and Co-first author)
CVPR 2022

PontTuset Disentangled high quality salient object detection
Lv Tang, Bo Li, Yi-Jie Zhong, Senyun Kuang, Shouhong Ding, Mofei Song
ICCV 2021