Chengkai Liu (刘成锴)

I am a fourth-year Ph.D. student in Computer Science at Texas A&M University (TAMU), advised by Prof. James Caverlee.

I received my bachelor’s degree in Computer Science from ACM Honors class, Shanghai Jiao Tong University (SJTU) in 2022, advised by Prof. Yong Yu.

My research interests include efficient recommender systems, large language models, and generative models. In Summer 2025, I interned at Amazon Prime Video, working on multimodal LLMs and personalized recommendation.

News

[10/2025] Invited to attend Meta’s first annual PhD Forum 2025. See you in the Bay Area!
[08/2025] Our DisastIR benchmark accepted to EMNLP 2025 Findings!
[05/2025] Paper on LLMs and conversational recommender systems accepted to Interspeech 2025!
[05/2025] Our FlowCF accepted to KDD 2025. See you in Toronto!
[12/2024] Joining Amazon as an Applied Scientist Intern in Summer 2025. See you in Seattle!
[09/2024] New survey on diffusion models for recommender systems available on arXiv.
[08/2024] Mamba4Rec selected for Best Paper Award at RelKD workshop (KDD 2024)!
[07/2024] Invited talk at Uber on Mamba4Rec and efficient sequential recommendation.
[07/2024] Our RecBLR accepted to CIKM 2024. See you in Boise!
[07/2024] Our Mamba4Rec accepted to RelKD workshop at KDD 2024 as Oral. See you in Barcelona!
[09/2023] SyMat accepted to NeurIPS 2023 as Spotlight (Top 3%)!

Selected Publications

Flow Matching for Collaborative Filtering

Chengkai Liu*, Yangtian Zhang*, Jianling Wang, Rex Ying, James Caverlee

KDD 2025 Presented at Meta PhD Forum 2025

PDF Code

Behavior-Dependent Linear Recurrent Units for Efficient Sequential Recommendation

Chengkai Liu, Jianghao Lin, Hanzhou Liu, Jianling Wang, James Caverlee

CIKM 2024

PDF Code

Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models

Chengkai Liu, Jianghao Lin, Jianling Wang, Hanzhou Liu, James Caverlee

RelKD @ KDD 2024 Best Paper Award Invited Talk at Uber

PDF Code

DisastIR: A Comprehensive Information Retrieval Benchmark for Disaster Management

Kai Yin, Xiangjue Dong, Chengkai Liu, Lipai Huang, Yiming Xiao, Zhewei Liu, Ali Mostafavi, James Caverlee

EMNLP 2025 Findings

PDF Code

I want a horror -- comedy -- movie: Slips-of-the-Tongue Impact Conversational Recommender System Performance

Maria Teleki, Lingfeng Shi, Chengkai Liu, James Caverlee

INTERSPEECH 2025

PDF Code

XYScanNet: An Interpretable State Space Model for Perceptual Image Deblurring

Hanzhou Liu, Chengkai Liu, Jiacong Xu, Peng Jiang, Mi Lu

NTIRE @ CVPR 2025

PDF

Towards Symmetry-Aware Generation of Periodic Materials

Youzhi Luo, Chengkai Liu, Shuiwang Ji

NeurIPS 2023 Spotlight (Top 3%)

PDF Code

Multi-Behavior Sequential Transformer Recommender

Enming Yuan, Wei Guo, Zhicheng He, Huifeng Guo, Chengkai Liu, Ruiming Tang

SIGIR 2022

PDF Code

Preprints

DMRetriever: A Family of Models for Improved Text Retrieval in Disaster Management

Kai Yin, Xiangjue Dong, Chengkai Liu, Allen Lin, Lingfeng Shi, Ali Mostafavi, James Caverlee

arXiv 2025

PDF Code

TwinCL: A Twin Graph Contrastive Learning Model for Collaborative Filtering

Chengkai Liu, Jianling Wang, James Caverlee

arXiv 2024

PDF Code

A Survey on Diffusion Models for Recommender Systems

Jianghao Lin, Jiaqi Liu, Jiachen Zhu, Yunjia Xi, Chengkai Liu, Yangtian Zhang, Yong Yu, Weinan Zhang

arXiv 2024

PDF Repo

CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics

Kai Yin, Bo Li, Chengkai Liu, Ali Mostafavi, Xia Hu

arXiv 2024

PDF

DeblurDiNAT: A Generalizable Transformer for Perceptual Image Deblurring

Hanzhou Liu, Binghan Li, Chengkai Liu, Mi Lu

arXiv 2024

PDF Code

Academic Service

Conference Reviewer: CIKM'23-24, KDD'24-26, NeurIPS'24-25, ICLR'25-26, ICML'25, SIGIR'25, WWW'25, AISTATS'25-26, ICWSM'25, AAAI'26.
Journal Reviewer: IEEE TKDE, IEEE TIST, ACM TKDD.

Misc.

My favorite singer is Jay Chou, and I have been his loyal fan for over a decade. I enjoy singing his songs and sharing them on Douyin.