Yan Jiang 姜彦

School of EECS, The University of Queensland, Australia

I am a PhD student at The University of Queensland (UQ), Australia. My research focuses on large language models (LLMs) and diffusion large language models (dLLMs), conducted under the supervision of Dr. Ruihong Qiu and Prof. Zi (Helen) Huang. I completed my dual Bachelor of Computer Science and Master of Data Science degrees at UQ under the supervision of Prof. Zi (Helen) Huang, graduating on 16 December 2023.

Publications

GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuning

Yan Jiang, Ruihong Qiu, Zi Huang

ICML 2026

We propose GFMate, a pre-training-agnostic test-time graph prompt tuning framework that exploits both labelled and unlabelled target-domain data for Graph Foundation Models.

Paper Code

Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models

Yan Jiang, Ruihong Qiu, Zi Huang

Preprint

We study block-size domain conflict in multi-domain RL post-training for dLLMs, introduce Block-R1-41K and Block-R1 benchmark, and propose sample-level best-improved training block sizes.

Paper Code

Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning

Yan Jiang, Ruihong Qiu, Zi Huang

ICML 2026

We propose b1, a post-training framework that learns dynamic-size reasoning blocks via Monotonic Entropy Descent with reinforcement learning to improve reasoning coherence in dLLMs.

Paper Code

Does Homophily Help in Robust Test-time Node Classification?

Yan Jiang, Ruihong Qiu, Zi Huang

WSDM 2026 - Oral

We propose GrapHoST, a label-free test-time graph structural transformation method that adaptively increases or decreases homophily to improve robust GNN node classification.

Paper Code

Balanced and Explainable Social Media Analysis for Public Health with Large Language Models

Yan Jiang, Ruihong Qiu, Yi Zhang, Peng-Fei Zhang

ADC 2023

We propose the ALEX framework for balanced and explainable social media analysis in public health using data augmentation and LLM-based explanation.

Paper

UQ at #SMM4H 2023: ALEX for Public Health Analysis with Social Media

Yan Jiang, Ruihong Qiu, Yi Zhang, Zi Huang

AMIA #SMM4H 2023

Our ALEX framework achieved top performance in SMM4H 2023 Tasks 2 and 4 via balanced training and LLM-based explanation for public health text classification.

Paper Code

Teaching · Education

Teaching

  • 2026: Tutor — Advanced Techniques for High Dimensional Data (INFS4205/7205), supervised by Dr. Yadan Luo
  • 2025: Tutor — Advanced Techniques for High Dimensional Data (INFS4205/7205), supervised by Dr. Yadan Luo
  • 2024: Tutor — Advanced Techniques for High Dimensional Data (INFS4205/7205), supervised by Dr. Yadan Luo
  • 2023: Tutor — Advanced Techniques for High Dimensional Data (INFS4205/7205), supervised by Prof. Zi (Helen) Huang
  • 2023: Tutor — Advanced Database Systems (INFS3200/7907), supervised by Dr. Yadan Luo
  • 2023: Tutor — Relational Database Systems (INFS2200/7903), supervised by Prof. Xue Li

Education

  • 2024–present: Doctor of Philosophy (PhD) in Computer Science, The University of Queensland
  • 2020–2023: Bachelor of Computer Science / Master of Data Science, The University of Queensland — graduated 16 December 2023