Portrait of Yunshan Ma

LMF · Multimodality & Forecasting

Yunshan Ma 马云山

Assistant Professor · Singapore Management University

School of Computing and Information Systems · Singapore

ysma@smu.edu.sg

Biography

I am a tenure-track Assistant Professor at Singapore Management University. My research centers on multimodality and forecasting. I lead LMF: Lab for Multimodality and Forecasting, where we connect multimodal modeling with forecasting across scales.

Before joining SMU, I was a Postdoctoral Research Fellow at the NExT++ Research Center, National University of Singapore, supervised by Prof. Tat-Seng Chua. I also worked with Prof. Chang Ee-Chien and Prof. Liang Zhenkai at the National Cybersecurity R&D Lab. I received my PhD from NUS in 2022, supervised by Prof. Chua.

I am interested in discovering and formulating new problems, and in developing data mining, information retrieval, and multimedia methods with practical impact.

Research Interests

Explore research →
01

Multimodality

Understanding and fusing text, images, audio, graphs, and symbolic data; modeling how their elements compose and combine.

Read more →
02

Forecasting

Anticipating macro-level events and micro-level behavior, from financial markets and geopolitics to users and cyber attacks.

Read more →
One paper accepted by Multimedia Modeling (MMM) 2027 of using Language Modeling for Bundle Construction!
BundleLM: Bundle Construction Using Language Model.[pdf come soon]
One paper gets accepted by TOIS of adapting MLLM for session recommendation, one paper gets accepted by SIGIR-AP of building a multimodal fashion understanding benchmark FashionStylist!
Distilling Transitional Patterns to Multimodal Large Language Models for Session-based Recommendation.[pdf]
FashionStylist: An Expert Knowledge-enhanced Multimodal Dataset for Fashion Understanding.[pdf] [dataset and code]
One paper gets accepted by CIKM on tokenization of GenRec, one paper gets accepted by EMNLP of reusing LLM reasoning for financial report generation!
Personalized Context-Conditioned Tokenization for Generative Recommendation.[pdf] [code]
AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation.[pdf] [code]
One paper gets accepted by TKDE about continual pre-training for recommendation, one demo paper gets accepted by ACMMM of applying visual analogy retrieval to financial K-line analysis!
Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training.[pdf]
FinAlogy: A Visual Analogy Retrieval System for Financial K-Line Analysis.[pdf coming soon][code] [video]
Our paper, Frozen LVLMs for Micro-Video Recommendation: A Systematic Study of Feature Extraction and Fusion, receives the best paper award of ICMR 2026!

Selected Publications

All publications →
ICMR · 2026

Frozen LVLMs for Micro-Video Recommendation: A Systematic Study of Feature Extraction and Fusion.

Best Paper Award · ICMR 2026

Huatuan Sun, Yunshan Ma, Changguang Wu, Yanxin Zhang, Pengfei Wang, Xiaoyu Du.

MMM · 2026

Integrating Symbolic and Waveform Music into Large Language Models.

Best Paper Award · MMM 2026

Teng Tu, Xiaohao Liu, Yunshan Ma, Ji Qi, Tat-Seng Chua.

ICAIF · Workshop · 2025

Reasoning on Time-Series for Financial Analysis.

Best Paper Award · ICAIF 2025 Workshop on Rethinking Financial Time-Series

Kelvin J.L. Koa, Jan Chen, Yunshan Ma, Huanhuan Zheng, Tat-Seng Chua.

MMAsia · Demo · 2025

VibeMus: Proactive Agentic System for Music Personalization.

Best Demo Award · MMAsia 2025

Zhiliang Guo, Teng Tu, Yunshan Ma, Xun Yang.

Computers & Security · 2025

AttacKG+: Boosting Attack Graph Construction with Large Language Models.

Yongheng Zhang, Tingwen Du, Yunshan Ma, Xiang Wang, Yi Xie, Guozheng Yang, Yuliang Lu, Ee-Chien Chang.

ICLR · 2025

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models.

Outstanding Paper Award · ICLR 2025

Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Jie Shi, Xiang Wang, Xiangnan He, Tat-Seng Chua.

WWW'24

Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models.

Kelvin J. L. Koa, Yunshan Ma*, Ritchie Ng, Tat-Seng Chua.

KDD'22

CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation.

Yunshan Ma, Yingzhi He, An Zhang, Xiang Wang, Tat-Seng Chua.

ICMR'21

Leveraging Two Types of Global Graph for Sequential Fashion Recommendation.

Best Student Paper Award · ICMR 2021

Yujuan Ding, Yunshan Ma, Wai Keung Wong, Tat-Seng Chua.

Background & Service

Education &
Experience

2025.01-present: Assistant Professor, School of Computing and Information Systems, Singapore Management University (SMU)
2022.04-2024.12: Postdoctoral Research Fellow, NExT++ Research Center, National University of Singapore (NUS)
Supervisor: Prof Tat-Seng Chua.
2017.08-2022.03: PhD in Computer Science, School of Computing, National University of Singapore
Supervisor: Prof Tat-Seng Chua.
2011-2015: Bachelor in Communication Engineering, Beijing University of Posts and Telecommunications (BUPT)

Honors &
Awards

  • Best Paper Award, ICMR 2026.
  • Best Paper Award, MMM 2026.
  • Best Demo Award, MMAsia 2025.
  • Best Paper Award, ACM ICAIF'25 Workshop on Rethinking Financial Time-Series.
  • Outstanding Paper Award, ICLR 2025.
  • Best Student Paper Award, ICMR 2021.
  • Research Achievement Award, National University of Singapore 2019.
  • Best Paper Finalist, ACMMM 2018.

Professional
Service

Conference Organizing Committee

Conference Workshops, Special Sessions, Special Issues

  • MMM 2027 Special Session: Multimodal Agentic Systems and Applications.
  • SIGIR 2025 Workshop: FinIR 2025: The 2nd Workshop on Financial Information Retrieval in the Era of Generative AI.
  • CIKM 2025 Workshop: International Workshop on Multimodal Generative Search and Recommendation.

Conference Session Chairs

Conference Program Committee

  • Area chair of WWW 2027, MMAsia 2026,KDD 2026.
  • Senior Program Committee (SPC) member of ICMR 2026.
  • Area chair of NLPCC 2025, 2026.
  • Area co-chair of CCL 2023.
  • PC member of ACMMM, SIGIR, KDD, WWW, WSDM, CIKM, IJCAI, ICML, ICLR, AAAI, ICMR, MMM etc.

Journal Editors

  • Associate Editor of Neurocomputing, from October 2026.

Journal Invited Reviewers

  • TKDE, TOIS, TMM, ToMM, TWeb, TIST, etc.