Qirun Zeng

Ph.D. candidate in Computer Science at City University of Hong Kong

My current research focus on how feedback shapes what bandit algorithms learn. When should a learner compare two options, and when should it measure the reward of just one? How easily can fabricated feedback steer it toward the wrong choice? My advisor is Prof. Jinhang Zuo.

I earned my bachelor’s degree at the University of Science and Technology of China, where I worked with Prof. Xue Chen and Prof. Jinhang Zuo, and later worked as a research assistant with Prof. Sibo Wang at the Chinese University of Hong Kong.

Selected Publications

⋆ Equal contribution.

View all publications

Recent News

  1. Two papers accepted to NeurIPS 2026.

  2. One paper accepted to Findings of EMNLP 2026.

  3. One Paper accepted to KDD 2026.

All updates

Service

Reviewer

2027

AISTATS and WWW.

2026

ICLR and NeurIPS.

2025

ICML and NeurIPS.

Programming

Account Rating Peak Solved

Updated

Explore topics & languages

388 platform solves across 4 accounts

Problems by topic

Problems can have multiple topics.

25topics
  1. Unclassified193
  2. Greedy78
  3. Math60
  4. Simulation58
  5. Dynamic programming45
  6. Brute force39
Other (20) 267
  • Constructive algorithms34
  • Sorting31
  • Other algorithms30
  • Data structures26
  • Search24
  • Binary search22
  • Strings16
  • Graphs13
  • Number theory13
  • Bitmasks10
  • Trees10
  • Two pointers9
  • Game theory8
  • Interactive6
  • Combinatorics5
  • Divide and conquer3
  • Geometry2
  • Hashing2
  • Scheduling2
  • Probability1

Languages

Problems can appear in multiple languages.

4languages
  1. C++242
  2. Not public82
  3. Python60
  4. C4
  5. Rust2

Topic coverage: Codeforces and Luogu. Language coverage: Codeforces, AtCoder and LeetCode. Missing data remains visible as Unclassified or Not public.