Jinyu Liu

Jinyu Liu

「刘金羽」

liujy24[AT]m.fudan.edu.cn

I am a second-year Ph.D. student at Fudan University, supervised by Henghui Ding and Yu-Gang Jiang.

News

  • 2026.05, 1 paper accepted to IEEE TIP.
  • 2026.05, 1 paper accepted to ICML 2026.

Education

  • 2024 - Present, Ph.D., Fudan University
  • 2020 - 2023, M.S., Fudan University
  • 2016 - 2020, B.S., Donghua University

Experience

  • 2023 - 2024, Computer Vision Engineer, Trip.com Group
  • 2022 - 2023, Research Intern, Tencent

Publications

ICML 2026
Unison

Unison: Benchmarking Unified Multimodal Models via Synergistic Understanding and Generation. ICML 2026.

Jinyu Liu, Xincheng Shuai, Henghui Ding, Yu-Gang Jiang.

Paper (upcoming)   Code (upcoming)

TIP 2026
EVIS

Event-Aware Instructed Assistant for Referring Video Segmentation. TIP 2026.

Jinyu Liu, Henghui Ding, Shuting He, Yu-Gang Jiang.

Paper

ACM MM 2022
MACIL-SD

Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection. ACM MM 2022.

Jiashuo Yu*, Jinyu Liu*, Ying Cheng, Rui Feng, Yuejie Zhang.

(*Equal Contribution)

Paper   Code

ICME 2022
ICME

Self-Supervised Video Representation Learning with Motion-Contrastive Perception. ICME 2022.

Jinyu Liu, Ying Cheng, Yuejie Zhang, Rui-Wei Zhao, Rui Feng.

Paper

Honors

  • 2023, Shanghai Outstanding Graduate
  • 2022, Huatai Securities Technology Scholarship, Fudan University

Services

  • Conference Reviewer for CVPR, ICML, NeurIPS, et al.
  • Journal Reviewer for TIP, et al.