Youhua Li中文
Illustrated Doraemon avatar wearing a graduation cap and holding a book

Decision Analytics · Operations · Artificial Intelligence

Youhua Li 李佑华

Ph.D. Student in Financial Decision Analytics & Operations

Researcher at AIFTHK · City University of Hong Kong

My research focuses on AI-driven decision-making and operations optimization, with broader interests in FinTech, quantitative finance, Web3, recommender systems, multimodal learning, large language models, and agents. I am particularly interested in combining LLM reasoning with verifiable optimization structure for complex operational and financial decisions.

Location
Hong Kong, China

Education

Ph.D. in Financial Decision Analytics & Operations

City University of Hong Kong

Advisors: Prof. Houmin Yan (Former Dean, College of Business, CityU; Chair Professor) and Prof. Zuojun (Max) Shen (Vice-President, HKU; Member of the Chinese Academy of Engineering). Research in AI-driven decision-making, operations optimization, FinTech, and large language models.

M.S. in Computer Science & Technology

ShanghaiTech University / Institute of Computing Technology, CAS (Joint Program)

Research in recommender systems, transfer learning, multimodal learning, and data mining.

B.Eng. in Automation Engineering

University of Electronic Science and Technology of China

Selected for the Liren Honors Class (40 students university-wide); undergraduate research in computer vision and 3D reconstruction.

News

Latest acceptances

  1. Wonderful news!

    Latent Reward Steering has been accepted to Findings of EMNLP 2026!

    Congratulations to Jiakang Li!

    EMNLP Findings

  2. Fantastic news!

    Four papers have been accepted to CIKM 2026!

    • Risk-Aware Reranking for Agentic Tool Retrieval
    • Recommender System as Slow and Fast Thinkers
    • ClinSDT: LLM-Encoded Clinical Semantic Guidance for Sepsis Treatment via Decision Transformer
    • On the Role of Language Representations in Auto-Bidding: Findings and Implications

    Congratulations to Qinfei Li, Zichen Yuan, Yanyan Wu, and Guanyu Zhu!

    CIKM

Research

01

AI for Operations

LLM-assisted optimization modeling, scheduling policy design, online decisions, queueing networks, and reinforcement learning.

02

FinTech, Web3 & Quantitative Finance

Supply-chain finance, financial reinforcement learning, quantitative trading, news-driven Web3 asset recommendation, utility modeling, and trading backtesting.

03

Recommender Systems

Multimodal and sequential recommendation, transfer learning, knowledge tracing, distillation, and model compression.

04

LLMs & Agents

Inference-time scaling, reward steering, skill evaluation, prompt optimization, code generation, and agent recommendation.

Publications

Under Review

29 papers
  1. 01

    LLM-Assisted Scheduling Policy Design and Refinement: Evidence Across Queueing Networks, Job-Shop Scheduling, and Ride-Hailing Dispatch

    Youhua Li, Sibo Xu, Yiqi Sun, Pengfei Guo, Zuojun (Max) Shen, Houmin Yan

    Production and Operations Management (Reject and Resubmit) · 2026Operations

    [Paper]
  2. 02

    Execution Authority in Digital Advertising: Coordinating Autobidding and Campaign Control

    Youhua Li, Yiqi Sun, Chang Liu, Zuojun (Max) Shen, Houmin Yan

    Production and Operations Management (Under Review) · 2026

  3. 03

    Principled Inference-Time Scaling: A Unified Framework for LLM-Based Optimization Modeling

    Yiqi Sun*, Youhua Li*, Zuojun (Max) Shen, Houmin Yan

    Operations Research (Reject and Resubmit) · 2026Optimization Modeling

    [Paper]
  4. 04

    α-Routing: Test-Time Skill Adaptation for Trading Agents via Counterfactual Valuation

    Yixuan Zhang, Sixu Chen, Boyi Zhang, Yongxin Ni, Youhua Li†

    (Under Review) · 2026

  5. 05

    SVAR: Semantics-Preserving Verification and Alignment Resolution for LLM-Based Clinical Field Alignment

    Ke Yan, Zhe Chen, Jining Luan, Youhua Li, Kerun Zhou, Jinchuan Zhang

    Under Review · 2026

  6. 06

    Diagnose, Then Allocate: Separating Language Reasoning from Portfolio Execution

    Yanlin Liu, Xinyu Fang, Yanyan Wu, Boyi Zhang, Guanyu Zhu, Zhehao Yu, Ye Chen, Hanwen Du, Yongxin Ni, Youhua Li

    Under Review · 2026

  7. 07

    FinMemRec: Dynamic Agent Memory for Financial Recommendation

    Jin Zhang, Hao Zeng, Xingyu Fang, Kerun Zhou, Binhua Xu, Zhe Chen, Jiaxin Wang, Hanwen Du, Youhua Li

    Under Review · 2026

  8. 08

    Beyond Uncertainty Reduction: Calibrated Planning for Interactive Diagnosis

    Yue Zhou, Haiyang Zhou, Jin Zhang, Kong Wang, Zihao Rao, Maolin Mao, Hanwen Du, Youhua Li

    Under Review · 2026

  9. 09

    From Relevance to Validity: Zero-Shot Tool Selection via Functional and Contextual Validation

    Xiaoxuan Dong, Jin Zhang, Zichen Yuan, Yue Zhou, Zihao Rao, Dexu Yu, Tingyong Wu, Wenhao Deng, Junchen Fu, Pengwei Sun, Yang Ran, Bo Lan, Yongxin Ni, Youhua Li

    Under Review · 2026

  10. 10

    Chain of Mindset: Reasoning with Adaptive Cognitive Modes

    Tianyi Jiang, Richuan An, Hengyi Feng, Naixin Zhai, Haodong Li, Xiaomin Yu, Jiahui Liu, Hanwen Du, Shuo Zhang, Zhi Yang, Jie Huang, Yifan Zhou, Yongxin Ni, Youhua Li, Huacan Wang, Ronghao Chen

    Under Review · 2026

    [Paper]
  11. 11

    Depth as a Candidate Source: Portfolio Allocation for Recurrent Test-Time Scaling in Large Language Models

    Chaoyuan Hao, Wentao Yue, Yanyan Wu, Boyuan Gao, Tianyou Lai, Maolin Wang, Yongxin Ni, Hanwen Du, Youhua Li

    Under Review · 2026

  12. 12

    Beyond Uniform Alignment: Rethinking Representation Fusion in Personalized LLM-based Recommendation

    Jining Luan, Zichen Yuan, Yichen Wu, Guanyu Zhu, Youhua Li†

    Under Review · 2026LLM-based Recommendation

  13. 13

    PSI-KT: Progressive State Inference for Knowledge Tracing

    Ke Yan, Jining Luan, Youhua Li, Zihao Rao, Ersheng Ni, Sicong Liu, Jinchuan Zhang

    Under Review · 2026Knowledge Tracing

  14. 14

    TACT: A Framework for Zero-Shot Task-to-Capability Transfer

    Xiaoxuan Dong, Zichen Yuan, Jin Zhang, Yue Zhou, Tingyong Wu, Dexu Yu, Wenhao Deng, Junchen Fu, Pengwei Sun, Yang Ran, Bo Lan, Youhua Li†, Yongxin Ni†

    Under Review · 2027AI Agents

  15. 15

    WitMem: Evidence-Witnessed Governance for Long-Term Agent Memory

    Shibo Liu, Jin Zhang, Yilong Liu, Tingyu Liang, Weihan Long, Yechen Qin, Zengrong Deng, Yiming Lin, Jining Luan, Zihao Rao, Dexu Yu, Pengwei Sun, Yang Ran, Hanwen Du, Youhua Li†, Yongxin Ni†

    Under Review · 2027Agent Memory

  16. 16

    From One Goal to Full-Call Success: Agent Reinforcement Learning with Reusable Experience for Autonomous IVR Navigation

    Zhe Fu, Guoqing Song, Frank Youhua Chen, Xinyu Fang, Youhua Li, Mengzhuo Guo

    Under Review · 2027Reinforcement Learning

  17. 17

    EVE-Bench: Entropy-Guided Benchmarking and Evaluation for Frontier Video Generation Models

    Nai-Xin Zhai, Qingyuan Hong, Xiao Jin, Liyuan Lillian Ma, Dexu Yu, Xuanqi Lan, Sihan Chen, Junchen Fu, Youhua Li†, Yongxin Ni†

    Under Review · 2027Video Generation

  18. 18

    Adaptive Hypercomplex Embeddings for Efficient and Expressive Recommender Systems

    Yihao Liu, Jiaxin Wang, Ersheng Ni, Jining Luan, Kong Wang, Kejie Huang, Xiaobing Feng, Jiacheng Liu, Xinyuan Song, Yongxin Ni, Min He†, Youhua Li†

    Under Review · 2026Recommender Systems

  19. 19

    SMKT-LLM: Semantic Mapping for Knowledge Tracing with Large Language Models

    Jiaxin Wang, Ersheng Ni, Hanwen Du, Sibo Xu, Jining Luan, Hao Zeng, Shuyan Xiong, Weihua Cheng, Chengzhi Xie, Yongxin Ni, Youhua Li†

    Knowledge-Based Systems (Under Review) · 2026Knowledge Tracing

  20. 20

    GIFT: LLM-Guided State-Reward Interface for Financial Reinforcement Learning

    Yanyan Wu, Boyi Zhang, Yanlin Liu, Xinyu Fang, Jining Luan, Meiqi Zhang, Jiacheng Liu, Hao Zeng, Dexu Yu, Chang Liu, Hanwen Du, Yongxin Ni, Youhua Li†

    Under Review · 2026FinTech

    [Paper]
  21. 21

    Dual-Timescale LLM-Guided Manager-Worker Reinforcement Learning for Ride-Hailing Dispatching and Repositioning

    Yuting Pang, Xinyu Fang, Yichen Wu, Xiaoxuan Dong, Kong Wang, Tianmin Sun, Sibo Xu, Hao Zeng, Dexu Yu, Jining Luan, Chunxiao Li, Hanwen Du, Youhua Li†

    Under Review · 2026Mobility

  22. 22

    W3α: A News-to-Alpha Benchmark for Utility-Driven Web3 Recommendation and Trading Backtesting

    Jining Luan, Hongji Li, Boyi Zhang, Xinyu Fang, Hanwen Du, Ersheng Ni, Hao Zeng, Jiacheng Liu, Yiqi Sun, Yongxin Ni†, Youhua Li†

    Under Review · 2026Web3

    [Paper]
  23. 23

    SkillPortrait: From Task-First Benchmarking to Skill-Centered Assessment of LLM Agent Skills

    Dexu Yu, Zhaoyang Guan, Xianhao Lin, Jining Luan, Zihao Rao, Xuanqi Lan, Yang Ran, Bo Lan, Naixin Zhai, Hanwen Du, Junchen Fu, Wenhao Deng, Yongxin Ni, Youhua Li

    Under Review · 2026Evaluation

    [Paper]
  24. 24

    Agent Skill Bundle Recommendation

    Jin Zhang, Jining Luan, Dexu Yu, Junchen Fu, Wenhao Deng, Hanwen Du, Xuanqi Lan, Joemon M. Jose, Youhua Li†, Yongxin Ni†

    Under Review · 2026AI Agents

  25. 25

    TriConList: Learning Tri-tier Contract Consistency for Full-Stack Repository Generation

    Xianhao Lin, Xinyu Fang, Wanglong He, Yichen Wu, Hongji Li, Jiacheng Liu, Dexu Yu, Hanwen Du, Sirui Hong, Chenglin Wu, Youhua Li†, Yongxin Ni†

    Under Review · 2026Code Generation

  26. 26

    Mitigating Modality Interference for Unified Reasoning and Perception in Multimodal Large Language Models

    Shuang Chen, Yimeng Ye, Dasen Dai, Yicheng Xiao, Wenxuan Huang, Kaixuan Fan, Manyuan Zhang, Yucheng Zhou, Hanwen Du, Haoxiao Wang, Ziqian Bi, Youhua Li†, Tianyu Shi†

    Under Review · 2026Multimodal LLMs

  27. 27

    PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models

    Chak-Wing Mak, Guanyu Zhu, Boyi Zhang, Hongji Li, Xiaowei Chi, Kevin Zhang, Yangfan He, Chun-Kai Fan, Wentao Lu, Kuangzhi Ge, Xinyu Fang, Hongyang He, Kuan Lu, Tianxiang Xu, Yongxin Ni, Youhua Li, Shanghang Zhang†

    Under Review · 2026World Models

    [Paper]
  28. 28

    A Meta-Optimization Framework for Prompt Optimization via Search Trajectory Learning

    Sibo Xu, Ersheng Ni, Jiaxin Wang, Weihua Cheng, Yuling Wu, Joseph Liu, Jiayi Zhang, Jincheng Fang, Yiqi Sun, Yongxin Ni, Youhua Li†

    Under Review · 2026Prompt Optimization

  29. 29

    Token Bayesian Optimization for Reasoning LLMs

    Weihua Cheng, Ersheng Ni, Lu Tianyou, Yuling Wu, Joseph Liu, Jiayi Zhang, Sirui Hong, Jiaqi Chen, Yiqi Sun, Jincheng Fang, Chenglin Wu, Youhua Li†, Yongxin Ni†

    Under Review · 2026Bayesian Optimization

    [Paper]

Published / Accepted

21 papers

2026

  1. 01

    Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

    Jiakang Li, Guanyu Zhu, Can Jin, Chenxi Huang, Dexu Yu, Ronghao Chen, Yang Zhou, Hongwu Peng, Xuanqi Lan, Dimitris N. Metaxas†, Youhua Li†

    Findings of EMNLP 2026 · 2026Reasoning LLMs

    [Paper]
  2. 02

    Risk-Aware Reranking for Agentic Tool Retrieval

    Qinfei Li, Xiaoxuan Dong, Jin Zhang, Dexu Yu, Wenhao Deng, Junchen Fu, Youhua Li, Hanwen Du, Chunxiao Li

    CIKM 2026 · 2026Agentic Tool Retrieval

  3. 03

    Recommender System as Slow and Fast Thinkers

    Zichen Yuan, Xiaoxuan Dong, Linkun Dai, Jinwei Yang, Jining Luan, Dexu Yu, Chunxiao Li, Joemon Jose, Youhua Li, Hanwen Du, Junchen Fu

    CIKM 2026 · 2026Recommender Systems

  4. 04

    ClinSDT: LLM-Encoded Clinical Semantic Guidance for Sepsis Treatment via Decision Transformer

    Yanyan Wu, Guanyu Zhu, Changbin Zhao, Jin Zhang, Dexu Yu, Tianmin Sun, Jining Luan, Chunxiao Li, Hanwen Du, Youhua Li†

    CIKM 2026 · 2026Decision Intelligence

  5. 05

    On the Role of Language Representations in Auto-Bidding: Findings and Implications

    Guanyu Zhu, Jining Luan, Hanwen Du, Xinyu Fang, Sibo Xu, Ersheng Ni, Hongji Li, Jincheng Fang, Ronghao Chen, Huacan Wang, Xuanqi Lan, Yongxin Ni, Yiqi Sun, Youhua Li†

    CIKM 2026 · 2026Auto-Bidding

    [Paper]
  6. 06

    Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation

    Nai-Xin Zhai, Weihua Cheng, Chenxi Huang, Yikai Gu, Hanwen Du, Dexu Yu, Junchen Fu, Yingwei Song, Liyuan Lillian Ma, Yangfan He, Yang Ran, Chunxiao Li, Youhua Li†, Yongxin Ni†

    ECCV 2026 · 2026Video Generation

  7. 07

    Interpretable Knowledge Tracing via Explicit-Implicit Alignment

    Ersheng Ni, Jiaxin Wang, Jining Luan, Jiacheng Liu, Shuyan Xiong, Mengmeng Chen, Yongxin Ni, Youhua Li†

    Knowledge-Based Systems · 2026Knowledge Tracing

    [Paper]
  8. 08

    Bridging NIP and MLM: A Unified Meta-Learning Framework for Personalized Sequential Recommendation

    Youhua Li†, Ersheng Ni, Yihao Liu, Junchen Fu, Hanwen Du, Yuanqi He, Yongxin Ni

    ACM TKDD · 2026Sequential Recommendation

    [Paper]

2025

  1. 09

    AMBER: Adaptive Meta Balanced Paradigm for Heterogeneous Graph-Based Knowledge Tracing

    Lifan Sun, Zichen Yuan, Ersheng Ni, Linkun Dai, Hongwei Jiang, Sibo Xu, Mengmeng Chen, Yucen Zhuang, Yongxin Ni, Youhua Li†

    CIKM 2025 · 2025Knowledge Tracing

    [Paper]
  2. 10

    Frequency-Decoupled Distillation for Efficient Multimodal Recommendation

    Ziyi Zhuang, Hongji Li, Junchen Fu†, Mengmeng Chen, Joemon M. Jose, Youhua Li, Yongxin Ni

    CIKM 2025 · 2025Multimodal Recommendation

    [Paper]
  3. 11

    SOLAR: Serendipity Optimized Language Model Aligned for Recommendation

    Zichen Yuan, Lifan Sun, Yucen Zhuang, Yue Wang, Xinyuan Song, Tianqi Xu, Siyuan Li, Jiaqi Chen, Joemon M. Jose, Youhua Li†, Yongxin Ni†

    Findings of EMNLP 2025 · 2025LLM Recommendation

    [Paper]
  4. 12

    Bridging the Gap: Teacher-Assisted Wasserstein Knowledge Distillation for Efficient Multi-Modal Recommendation

    Ziyi Zhuang, Hanwen Du, Youhua Li, Junchen Fu, Joemon M. Jose, Yongxin Ni†

    WWW 2025 · 2025Knowledge Distillation

    [Paper]
  5. 13

    Teach Me How to Denoise: A Universal Framework for Denoising Multi-modal Recommender Systems via Guided Calibration

    Hongji Li, Hanwen Du, Youhua Li, Junchen Fu, Chunxiao Li, Ziyi Zhuang, Jiakang Li, Yongxin Ni†

    WSDM 2025 · 2025Multimodal Recommendation

    [Paper]
  6. 14

    Video-Bench: Human-Aligned Video Generation Benchmark

    Hui Han, Siyuan Li, Jiaqi Chen, Yiwen Yuan, Yuling Wu, Chak Tou Leong, Hanwen Du, Junchen Fu, Youhua Li, Jie Zhang, Chi Zhang, Li-jia Li, Yongxin Ni†

    CVPR 2025 · 2025Video Generation

    [Paper]
  7. 15

    A Content-Driven Micro-Video Recommendation Dataset at Scale

    Yongxin Ni, Xiangyan Liu, Youhua Li, Junjie Shan, Jiaqi Zhang, Junchen Fu, Yu Cheng, Fajie Yuan†

    CIKM 2025 · 2025Dataset

    [Paper]

2024

  1. 16

    An Empirical Study of Training ID-Agnostic Multi-modal Sequential Recommenders

    Youhua Li, Hanwen Du, Yongxin Ni, Yuanqi He, Junchen Fu, Xiangyan Liu

    arXiv · 2024Multimodal Recommendation

    [Paper]
  2. 17

    NineRec: A Suite of Transfer Learning Datasets for Modality-Based Recommender Systems

    Jiaqi Zhang, Yu Cheng, Yongxin Ni, Zheng Yuan, Junchen Fu, Youhua Li, Jie Wang, Fajie Yuan†

    IEEE TPAMI · 2024Dataset

    [Paper]
  3. 18

    Multi-Modality is All You Need for Transferable Recommender Systems

    Youhua Li, Hanwen Du, Yongxin Ni, Pengpeng Zhao, Qi Guo†, Fajie Yuan†, Xiaofang Zhou

    ICDE 2024 · 2024Transfer Learning

    [Paper]

2023

  1. 19

    Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited

    Zheng Yuan, Fajie Yuan, Yu Song, Youhua Li, Junchen Fu, Fei Yang, Yongxin Ni

    SIGIR 2023 · 2023Recommender Systems

    [Paper]

2021

  1. 20

    Shape Transformer Nets: Generating Viewpoint-Invariant 3D Shapes from a Single Image

    Jinglun Yang*, Youhua Li*, Lu Yang

    Journal of Visual Communication and Image Representation · 20213D Vision

    [Paper]

2020

  1. 21

    VST3D-Net: Video-Based Spatio-Temporal Network for 3D Shape Reconstruction from a Video

    Jinglun Yang, Guanglun Zhang, Youhua Li, Lu Yang

    International Conference on 3D Immersion · 20203D Vision

    [Paper]

* Equal contribution. † Corresponding author.

Research Experience

Researcher & Ph.D. Student

AIFTHK / City University of Hong Kong

Advisor(s): Prof. Houmin Yan; Prof. Zuojun (Max) Shen

Supply-chain finance modeling, LLM-enhanced decision systems, e-commerce GEO frameworks, and quantitative finance.

Research Assistant

School of Management, University of Science and Technology of China

Advisor(s): Prof. Chunxiao Li; Prof. Eric Zheng; Prof. Bin Gu

Large language models, behavioral finance, and financial information systems.

Research Assistant

CUHK Business School

Advisor(s): Prof. Jing Wu

LLMs and agents for operations management and supply chains.

Visiting Student

Representation Learning Lab, Westlake University

Advisor(s): Prof. Fajie Yuan

Data mining, transfer learning, and multimodal recommendation.

Research Intern

Shanghai Research Center for Brain Science and Brain-Inspired Intelligence

Advisor(s): Prof. Yi Zhou

NLP commonsense reasoning and knowledge graphs for investment management.

Undergraduate Researcher

Pattern Recognition and Machine Intelligence Lab, UESTC

Advisor(s): Prof. Lu Yang

3D reconstruction, SLAM, and computer vision.

Professional Service

Journal reviewing and conference program committee / reviewing service

Journals
ACM TOIS · ACM TKDD · Information Processing & Management · Computers & Education: Artificial Intelligence · FLLM
Senior Program Committee
CIKM 2026
Program Committee
AAAI 2025 / 2026 · WSDM 2026 · KDD 2024 / 2025 / 2026
Conference Reviewer
ACM MM 2024 / 2025 / 2026 · ICLR 2024 / 2025 · CIKM 2025
Workshops
DCAI Workshop at WWW 2024