Peking University · CFCS

Yuqing Kong

Tenured Associate Professor

I am a tenured associate professor at the Center on Frontiers of Computing Studies (CFCS), Peking University. My research lies at the intersection of theoretical computer science and economics, with interests in information elicitation and evaluation, prediction markets, mechanism design, and applications to crowdsourcing and machine learning.

I received my B.S. in Mathematics from the University of Science and Technology of China in 2013 and my Ph.D. in Computer Science and Engineering from the University of Michigan in 2018, advised by Grant Schoenebeck.

Email DBLP ORCID

Research

Selected publications

Dominantly Truthful Peer Prediction Mechanisms with a Finite Number of Tasks

Y. Kong

Journal of the ACM (JACM), 71(2), Article 9, 2024.

Illustration for DMI-Mechanism — DMI-Mechanism

Eliciting Thinking Hierarchy without a Prior

Y. Kong, Y. Li, Y. Zhang, Z. Huang, J. Wu

Neural Information Processing Systems (NeurIPS), 2022. Blog

Ranked answer-prediction matrices from Eliciting Thinking Hierarchy without a Prior — Answer-prediction Matrices

Dominantly Truthful Multi-task Peer Prediction with a Constant Number of Tasks

Y. Kong

ACM-SIAM Symposium on Discrete Algorithms (SODA), 2020. Talk Blog

L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise

Y. Xu*, P. Cao*, Y. Kong, Y. Wang

Neural Information Processing Systems (NeurIPS), 2019. Blog

Illustration for the LDMI loss function paper — LDMI Loss Function

An Information Theoretic Framework For Designing Information Elicitation Mechanisms That Reward Truth-telling

Y. Kong, G. Schoenebeck

ACM Transactions on Economics and Computation (TEAC), 7(1), 2019.

Publications

2026

Decision Aggregation under Quantal Response

Z. Huang, Y. Xia, Y. Kong

International Conference on Learning Representations (ICLR), 2026. arXiv

PMIScore: An Unsupervised Approach to Quantify Dialogue Engagement

Y. Guo, Z. Huang, Y. Kong

The ACM Web Conference (WWW), 2026, pp. 99–110. arXiv

2025

Algorithmic Robust Forecast Aggregation

Y. Guo, J. D. Hartline, Z. Huang, Y. Kong, A. Shah, F.-Y. Yu

ACM Conference on Economics and Computation (EC), 2025.

Benchmarking LLMs' Judgments with No Gold Standard

S. Xu, Y. Lu, G. Schoenebeck, Y. Kong

International Conference on Learning Representations (ICLR), 2025.

Mitigating the Participation Bias by Balancing Extreme Ratings

Y. Guo, Y. Kong, J. Liu

The ACM Web Conference (WWW), 2025. Oral presentation.

Robust Aggregation with Adversarial Experts

Y. Guo, Y. Kong

The ACM Web Conference (WWW), 2025.

Learning against Non-credible Second-Price Auctions

Q. Wang, X. Xia, Z. Yang, X. Deng, Y. Kong, Z. Zhang, L. Wang, C. Yu, J. Xu, B. Zheng

The ACM Web Conference (WWW), 2025.

Earlier publications · 2016–2024

2024

The Surprising Benefits of Base Rate Neglect in Robust Aggregation

Y. Kong, S. Wang, Y. Wang

ACM Conference on Economics and Computation (EC), 2024.

Eliciting Informative Text Evaluations with Large Language Models

Y. Lu, S. Xu, Y. Zhang, Y. Kong, G. Schoenebeck

ACM Conference on Economics and Computation (EC), 2024.

Dominantly Truthful Peer Prediction Mechanisms with a Finite Number of Tasks

Y. Kong

Journal of the ACM (JACM), 71(2), Article 9, 2024. Extends SODA 2020 and ITCS 2022.

Robust Decision Aggregation with Second-order Information

Y. Pan, Z. Chen, Y. Kong†

The ACM Web Conference (WWW), 2024.

2023

False Consensus, Information Theory, and Prediction Markets

Y. Kong, G. Schoenebeck

Innovations in Theoretical Computer Science (ITCS), 2023.

Calibrating “Cheap Signals” in Peer Review without a Prior

Y. Lu, Y. Kong

Neural Information Processing Systems (NeurIPS), 2023.

Near-optimal Experimental Design under the Budget Constraint in Online Platforms

Y. Guo, Y. Yuan, J. Zhang, Y. Kong, Z. Zhu, Z. Cai

The ACM Web Conference (WWW), 2023.

Learning to Bid in Repeated First-price Auctions with Budgets

Q. Wang, Z. Yang, X. Deng, Y. Kong

International Conference on Machine Learning (ICML), 2023.

2022

Eliciting Thinking Hierarchy without a Prior

Y. Kong, Y. Li, Y. Zhang, Z. Huang, J. Wu

Neural Information Processing Systems (NeurIPS), 2022. Blog

BONUS! Maximizing Surprise

Z. Huang, Y. Kong, X. Liu, G. Schoenebeck, S. Xu

The Web Conference (WWW), 2022.

More Dominantly Truthful Multi-task Peer Prediction with a Finite Number of Tasks

Y. Kong

Innovations in Theoretical Computer Science (ITCS), 2022.

2021

SURPRISE! and When to Schedule It

Z. Huang*, S. Xu*, Y. Shan, Y. Lu, Y. Kong, X. Liu, G. Schoenebeck

International Joint Conference on Artificial Intelligence (IJCAI), 2021.

2020

Dominantly Truthful Multi-task Peer Prediction with a Constant Number of Tasks

Y. Kong

ACM-SIAM Symposium on Discrete Algorithms (SODA), 2020. Talk Blog

TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning

X. Sun*, Y. Xu*, P. Cao, Y. Kong, L. Hu, S. Zhang, Y. Wang

European Conference on Computer Vision (ECCV), 2020. Oral (2%).

Information Elicitation Mechanisms for Statistical Estimation

Y. Kong, G. Schoenebeck, B. Tao, F. Yu

AAAI Conference on Artificial Intelligence (AAAI), 2020.

2019

Outsourcing Computation: the Minimal Refereed Mechanism

Y. Kong, C. Peikert, G. Schoenebeck, B. Tao

Web and Internet Economics (WINE), 2019.

L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise

Y. Xu*, P. Cao*, Y. Kong, Y. Wang

Neural Information Processing Systems (NeurIPS), 2019. Blog

Max-MIG: an Information-Theoretic Approach for Joint Learning from Crowds

P. Cao*, Y. Xu*, Y. Kong, Y. Wang

International Conference on Learning Representations (ICLR), 2019.

f-Similarity Preservation Loss for Soft Labels: A Demonstration on Cross-Corpus Speech Emotion Recognition

B. Zhang*, Y. Kong*, G. Essl, E. M. Provost

AAAI Conference on Artificial Intelligence (AAAI), 2019.

An Information Theoretic Framework For Designing Information Elicitation Mechanisms That Reward Truth-telling

Y. Kong, G. Schoenebeck

ACM Transactions on Economics and Computation (TEAC), 7(1), 2019.

2018

Eliciting Expertise without Verification

Y. Kong, G. Schoenebeck

ACM Conference on Economics and Computation (EC), 2018.

Water from Two Rocks: Maximizing the Mutual Information

Y. Kong, G. Schoenebeck

ACM Conference on Economics and Computation (EC), 2018.

Equilibrium Selection in Information Elicitation without Verification via Information Monotonicity

Y. Kong, G. Schoenebeck

Innovations in Theoretical Computer Science (ITCS), 2018.

Optimizing Bayesian Information Revelation Strategy in Prediction Markets: the Alice Bob Alice Case

Y. Kong, G. Schoenebeck

Innovations in Theoretical Computer Science (ITCS), 2018.

2016

Putting Peer Prediction Under the Micro(economic)scope and Making Truth-telling Focal

Y. Kong, K. Ligett, G. Schoenebeck

Web and Internet Economics (WINE), 2016.

Talks

Tutorials & talks

Eliciting Information without Verification

Invited talk, IJTCS-FAW, 2022.

Dominantly Truthful Multi-task Peer Prediction with a Constant Number of Tasks

Invited talk, Incentives in Machine Learning Workshop, ICML, 2020.

Eliciting Information by Information Theory

Invited talk, Women in EconCS, WINE, 2020.

An Information Theoretic View of Information Elicitation Mechanisms

Tutorial with Grant Schoenebeck, ACM Conference on Economics and Computation (EC), 2017.

Service

Professional service

ACM Conference on Economics and Computation (EC)

Track Chair, 2026.

Program Committee, 2019–2022 and 2024–2025.

Conference on Web and Internet Economics (WINE)

Program Committee Co-Chair, 2023, with Jugal Garg and Max Klimm.

Senior Program Committee, 2022 and 2024–2026 · Program Committee, 2021.

Highlights Beyond EC Committee

ACM Conference on Economics and Computation (EC), 2023.

International Colloquium on Automata, Languages, and Programming (ICALP)

Program Committee, Track A, 2022.

Workshops & tutorials

Organizer, Information Acquisition Workshop, EC 2024, with Yingkai Li and Yifan Wu.

Organizer, Mechanism Design workshop/day, WALE 2024, Kefalonia, Greece.

Organizer, An Information Theoretical View of Information Elicitation Mechanisms, EC 2017, with Grant Schoenebeck.

University and departmental service

Mentor, Turing Class of 2018. Initiated activities including the CS Frontier Tutorial, CS Peer Talks, board-game nights, and science-fiction reading sessions.

Member, Research Mentor Committee of the Turing Class.

Member, Peking University Admission Committee for Anhui Province.

Teaching

Courses

Randomized Algorithms

Spring · 2019–2026

Probabilistic techniques for the design and analysis of algorithms, including concentration, randomized constructions, random walks, and Markov-chain methods.

Course materials draw in part on Alistair Sinclair’s Randomness and Computation lecture notes.

Preview of Cards for Randomness & Computation Student projectCards for Randomness & Computation ↗

Mathematics for the Information Age

Fall · 2020–2026

A mathematical introduction to modern data science, including high-dimensional geometry, spectral methods, random walks, large graphs, learning, and algorithms for massive data.

At Peking University, the course was initiated by John Hopcroft, and I continued teaching it afterward. The primary text is Foundations of Data Science by Avrim Blum, John Hopcroft, and Ravindran Kannan.

Previously: Algorithmic Game Theory, Fall 2019.

Students

Current Ph.D. students

Yuxuan Lu

Entered 2022

Ying Wang

Entered 2023 · co-advised with Xiaotie Deng

Mingyu Song

Entered 2024 · co-advised with Yizhou Wang

Yichong Xia

Entered 2025

Weinan Qian

Entered 2025

Jialiang Liu

Entered 2026

Ph.D. alumni

Qian Wang

Entered 2019 · ByteDance

Zhihuan Huang

Entered 2021 · DeepSeek

Yongkang Guo

Entered 2021 · Huawei

Random

Random drawing

A hand-drawn comic of a diner ordering proofs of famous open problems from a waiter — I’ll have a proof of the Twin Prime Conjecture

Comic by Yuqing Kong · Inspired by a scene from The Million Pound Note (1954)

“I’ll have a proof of the Twin Prime Conjecture, and an elegant solution to P vs. NP, with proofs of all the related corollaries. Make it a nice, thick manuscript.”

“It’ll cost quite a few tokens.”

“I know. And add an explanation simple enough for a high school student to follow.”

Random AI animation

Early pieces, made casually, when the technology was still limited. All of them are based on the science fictions in my wechat public account 麦金太尔街1844号.

狼人杀中的数学

讨论各个角色的人数该怎么设，对抗角色之间的博弈均衡分析，以及如何用经济学理论分析角色设计对观看体验的影响。和这套理论相关的论文见 SURPRISE! and When to Schedule It（IJCAI 2021，关于英雄联盟比赛观看的实验）和 BONUS! Maximizing Surprise（WWW 2022，关于问答游戏分数的设计理论）。