Xue Geng

Research Scientist, Institute for Infocomm Research, A*STAR

Joined

February 2018

Names

Xue Geng

Emails

****@i2r.a-star.edu.sg (Confirmed)

****@gmail.com (Confirmed)

****@a-star.edu.sg (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Research Scientist

Institute for Infocomm Research, A*STAR (i2r.a-star.edu.sg)

2017 – Present

PhD student

National University of Singapore (nus.edu.sg)

2012 – 2017

Advisors, Relations & Conflicts

Coauthor

Wang Zhe

2019 – 2023

Coauthor

Tat-seng Chua

2012 – 2017

PhD Advisor

Chua Tat-Seng

2012 – 2017

Coauthor

Hanwang Zhang

2014 – 2016

Coauthor

Yang Yang

2014 – 2015

Expertise

model compression

model quantization

knowledge distillation

network pruning

2017 – 2023

Deep Network Compression

2018 – 2022

Multimedia Content Analysis

2012 – 2017

Publications

CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning
Jingze Ge, Xue Geng, Yun Liu, Wanqi Dong, Wang Zhe Mark, Ngai-Man Cheung, Min Wu, Xulei Yang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion
Wang Zhe Mark, Kaixin Xu, Xue Geng, Fen Fang, Mohamed M. Sabry Aly, Xulei Yang, Min Wu, Weisi Lin
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Distribution-Aware Diffusion Model Quantization via Distortion Minimization
Wang Zhe Mark, Fen Fang, Xu Kaixin, Hongyuan Zhu, Ying Sun, Xue Geng, Xulei Yang, Min Wu, Weisi Lin
- Submitted to ICLR 2025
- Readers: Everyone
DM3D: Parameter-Efficient and Lossless 3D Object Detection via Distortion Minimization
Kaixin Xu, qingtian feng, Hao Chen, HU TIHUA, Wang Zhe Mark, Xue Geng, Xulei Yang, Min Wu, Xiaoli Li, Weisi Lin
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming
Lorenzo Orecchia, Jiawei Hu, Xue He, Wang Zhe Mark, Xulei Yang, Min Wu, Xue Geng
- NeurIPS 2024 poster
- Readers: Everyone
LSP: Low-Power Semi-structured Pruning for Vision Transformers
Kaixin Xu, Zhe Wang, Chunyun Chen, Xue Geng, Jie Lin, Min Wu, Xiaoli Li, Weisi Lin
- Submitted to ICLR 2024
- Readers: Everyone
MABA-Net: Masked Additive Binary Activation Network
Xue Geng, Jiawei Hu, Jie Lin, Zhe Wang, Shaohua Li, Min Wu, Mohamed M. Sabry Aly
- 22 Sept 2022 (modified: 13 Feb 2023)
- ICLR 2023 Conference Withdrawn Submission
- Readers: Everyone
CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
Xiuchao Sui, Shaohua Li, Xue Geng, Yan Wu, Xinxing Xu, Yong Liu, Rick Siow Mong Goh, Hongyuan Zhu
- 31 Mar 2022 (modified: 27 Nov 2023)
- OpenReview Archive Direct Upload
- Readers: Everyone
Delving into Channels: Exploring Hyperparameter Space of Channel Bit Widths with Linear Complexity
Zhe Wang, Jie Lin, Xue Geng, Mohamed M. Sabry Aly, Vijay Chandrasekhar
- 29 Sept 2021 (modified: 13 Feb 2023)
- ICLR 2022 Conference Withdrawn Submission
- Readers: Everyone
Learning Image and User Features for Recommendation in Social Networks
Xue Geng, Hanwang Zhang, Jingwen Bian, Tat-Seng Chua
- 2015 (modified: 07 Jan 2026)
- ICCV 2015
- Readers: Everyone

Co-Authors

View all 34 co-authors