🎈 About Me

I am a Ph.D. student in Artificial Intelligence at South China University of Technology (SCUT), advised by Prof. Kaixiang Yang and co-advised by Prof. Zhiwen Yu and Prof. C. L. Philip Chen. I also work closely with Prof. Carl Yang at Emory University. Previously, I received my master's degree from City University of Hong Kong, where I was advised by Prof. Xiangyu Zhao.

My research focuses on recommendation, graph out-of-distribution generalization, large language models, continual learning, and generative models. I am currently a research intern at DiDi, working on on-policy self-distillation for diffusion language models and long-video agents. Previously, I was a research intern at Xiaohongshu.

My work has appeared at WWW, KDD, ICML, IEEE TKDE, and Information Fusion, including oral presentations at WWW 2026 and KDD 2026. I am a recipient of the 2026 National Scholarship for Doctoral Students and President's Scholarship (Highest Honor).

📰 News

2026.10

Received the 2026 National Scholarship for Doctoral Students and President's Scholarship (Highest Honor).

2026.08

Started a research internship at DiDi, working on diffusion language models and long-video agents.

2026

Cognitive Bifurcation and C-HyPOD appear as Oral papers at KDD 2026 and WWW 2026.

2026

Democratic Recommendation was published in IEEE Transactions on Knowledge and Data Engineering.

2026.04

Started a research internship at Xiaohongshu in the Recommendation Algorithms Group II.

2025

Diffusion masked autoencoders was published in Information Fusion.

📝 Publications

† Equal contribution   ·   * Corresponding author   ·   Google Scholar

Published papers

KDD 2026Oral

Cognitive Bifurcation: Dual-Progressive Causal Diffusion with Hippocampal Memory for Continual Graph Learning

Jiahao Liang, Carl Yang, Haoran Yang, Zhiwen Yu, Mengzhu Wang, and Kaixiang Yang

ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2026

WWW 2026Oral

C-HyPOD: Causal Hyperbolic Representation Learning with Prototype Orthogonal Disentanglement for Graph Out-of-Distribution Recommendation

Jiahao Liang†, Yutian Xiao†, Haoran Yang, Zhiwen Yu, Jia-Nan Liu, and Kaixiang Yang

The ACM Web Conference, 6541–6550, 2026

TKDE 2026

Democratic Recommendation with User and Item Representatives Produced by Graph Condensation

Jiahao Liang†, Haoran Yang†, Xiangyu Zhao, Zhiwen Yu, Guandong Xu, Wanyu Wang, and Kaixiang Yang

IEEE Transactions on Knowledge and Data Engineering, 38(5):2670–2686, 2026

ICML 2026

Video-BCI: Bayesian Cognitive Integration of Self-Prior Hypotheses for Video Understanding

Xing Xi, Peixian Chen, Yu Qiu, Ronghua Luo, Peilin Tong, and Jiahao Liang*

International Conference on Machine Learning, 2026

Information Fusion 2025

Diffusion masked autoencoders as causal-aware curriculum learner for graph out-of-distribution generalization

Jiahao Liang, Wuxing Chen, Zhiwen Yu, Tong Zhang, C. L. P. Chen, and Kaixiang Yang

Information Fusion, 103792, 2025

WWW 2023

Mmmlp: Multi-modal multilayer perceptron for sequential recommendations

Jiahao Liang, Xiangyu Zhao, Muyang Li, Zijian Zhang, Wanyu Wang, Haochen Liu, and Zitao Liu

Proceedings of the ACM Web Conference, 1109–1117, 2023

Preprints

arXiv 2025

Large Language Model Enhanced Graph Invariant Contrastive Learning for Out-of-Distribution Recommendation

Jiahao Liang, Haoran Yang, Xiangyu Zhao, Zhiwen Yu, Mianjie Li, Chuan Shi, and Kaixiang Yang

arXiv preprint arXiv:2511.18282, 2025

Co-authored papers and preprints

arXiv 2026

ReliGRec: Reliability-Oriented LLM-Based Generative Recommendation via User-Risk-Aware Prompt Routing

Haoran Yang, Fei Chen, Yutian Xiao, and Jiahao Liang

arXiv preprint arXiv:2609.16560, 2026

arXiv 2026

OneModel: A Unified Foundation for Platform-Scale Multi-Scenario Ranking

Yinqi Zhang, Peiyu Hu, Yuntian Tang, Siying Gu, Jiahao Liang, et al.

arXiv preprint arXiv:2608.18606, 2026

Xiaohongshu Internship research

arXiv 2026

Hierarchical Latent Reasoning for LLM-based Recommendation

Peiyu Hu, Siying Gu, Weihai Lu, Zhuodong Liu, Yuntian Tang, Jiahao Liang, et al.

arXiv preprint arXiv:2607.27760, 2026

Xiaohongshu Internship research

ISKE 2026

Adaptive Semi-supervised Ensemble for Tumor Data Classification

Guojie Li, Ziwei Fan, Jiahao Liang, and Zhiwen Yu

International Conference on Intelligent Systems and Knowledge Engineering, 319–336, 2026

📖 Education

South China University of Technology

Sep. 2023 – Present

Ph.D. Student in Artificial Intelligence · Guangzhou, China

Advisor: Prof. Kaixiang Yang
Co-advisors: Prof. Zhiwen Yu and Prof. C. L. Philip Chen

City University of Hong Kong

Sep. 2021 – Feb. 2023

Master's in Electrical and Electronic Engineering · Hong Kong

Advisor: Prof. Xiangyu Zhao

💻 Experience

DiDi

DiDi

Aug. 2026 – Present

Research Intern

  • DLLM-OPSD: On-policy self-distillation for diffusion language models, jointly modeling reveal-position and token decisions.
  • LongVideoAgent-OPSD: Observation-conditioned action distillation for long-video agents, integrating evidence retrieval and visual inspection.
Xiaohongshu

Xiaohongshu

Apr. 2026 – Aug. 2026

Research Intern · Recommendation Algorithms Group II

  • Cross-scenario generative recommendation and platform-scale ranking with OneModel.
  • Long-sequence modeling, latent reasoning, and token compression for recommendation.
  • Internship research: OneModel and HiLaR.

🍀 Services

Reviewer / External Reviewer

  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
  • AAAI Conference on Artificial Intelligence (AAAI), 2025, 2026
  • The ACM Web Conference (WWW), 2026
  • ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026
  • IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025, 2026
  • IEEE Transactions on Big Data (TBD), 2024
  • International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2023
  • ACM International Conference on Information and Knowledge Management (CIKM), 2023