Kangning Cui

Assistant Professor of Data ScienceCity University of Hong Kong (Dongguan)

Office: AC4-422

Efficient and reliable machine learning.

I study model compression, uncertainty, and learning with limited labels across language models, geospatial data, and healthcare.

PhD and research assistant opportunities. Join the group.

Email CityU-DG Profile GitHub Scholar

Selected Research

All research

Efficient & Reliable ML

Understanding the cost of compression

LowRankArena overview: evaluation challenges, a standardized SVD-compression platform, and findings on accuracy and inference efficiency

LowRankArena evaluates the accuracy and inference efficiency of compressed language models under shared tasks and budgets.

NeurIPS'26, ED Track, Poster

Co-first author

Preprint Code

Geospatial AI

From aerial imagery to forest maps

PRISM workflow: aerial forest imagery, palm detection, segmentation, and geographic mapping

PRISM and PalmDSNet detect and locate canopy palms, connecting aerial imagery with forest maps and spatial modeling.

IJCAI'25, Oral TGRS'25

Co-first and corresponding author

Project overview Paper Code

Medical AI

Extending the reach of ECG models

Overview of extending frozen 10-second ECG foundation models to longer recordings with a lightweight plug-in module

A lightweight module extends pretrained ECG models to longer recordings without retraining the backbone.

NeurIPS'26, Poster

Co-author

Preprint

Recent News

[09/2026]

LowRankArena accepted at NeurIPS'26, ED Track, Poster.

[09/2026]

Extending ECG foundation models to longer recordings accepted at NeurIPS'26, Poster.

[08/2026]

DPQ: preserving uncertainty in quantized language models accepted at EMNLP'26, Findings.

[08/2026]

GeoTALOS, our geoscience platform, accepted at SIGSPATIAL'26.

Earlier news

[06/2026]

The paper "JassidNet as a Quantization-Aware Lightweight Phenotyping Framework for High-Throughput Cotton Jassid (Amrasca biguttula) Detection and Counting Toward Objective Resistance Screening" was accepted by Ind. Crops Prod..

[04/2026]

The paper "DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions" was accepted by ICML 2026 (Spotlight).

[04/2026]

The paper "AwakeForest: An Interactive Geospatial Platform for Large-Scale Forest Imagery" was accepted by IJCAI Demo 2026.

[04/2026]

The paper "Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection" was accepted by ICMR 2026.

Join the group

PhD opportunities at CityU and research assistant positions at CityU-DG. For CityU-DG projects, feel free to email me to discuss your interests.

Application details

Appointments

2026–Present

City University of Hong Kong (Dongguan)

Assistant Professor of Data Science

2025–Present

Andrew Sabin Family Center for Environment and Sustainability

Robert J. Plemmons Fellow

2025–2026

Wake Forest University

Research Assistant Professor, Department of Computer Science

Education

2021–2025

Ph.D. in Mathematics

City University of Hong Kong & Hong Kong Centre for Cerebro-Cardiovascular Health Engineering

Medical and remote sensing image/signal analysis. Advisors: Prof. Raymond H. Chan and Prof. Jean-Michel Morel.

2024–2025

Visiting DPhil Student in Biomedical Engineering

University of Oxford

Ultrasound video analysis and biomedical imaging. Advisor: Prof. Alison Noble.

2017–2021

B.S. in Computing Mathematics

City University of Hong Kong

First Class Honours · Minor in Computer Science.

2020

Exchange Student, Applied Mathematics

Delft University of Technology

Delft, Netherlands.