Jiacheng Hou

Data Science and Information Technology

I am a PhD candidate at SIGS, Tsinghua University (since 2024). My recent work studies video generation, multi-agent systems, RLHF for MLLMs and diffusion models, vision-centric jailbreaks, video inpainting, and graph learning for functional brain networks. Feel free to contact me if you are interested in my work.

Selected Publications

Comparison of different multi-agent systems

NeurIPS 2026 Learning When to Collaborate: Selective Multi-Agent Medical Reasoning via Uncertainty-Aware Routing

Jiacheng Hou, Xueliang Cui, Dan Lu, Ruxin Wang

Comparison of text-centric and vision-centric image-editing attacks

ICML 2026 When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models Spotlight & Oral

Jiacheng Hou, Yining Sun, Ruochong Jin, Haochen Han, Fangming Liu, Wai Kin Victor Chan, Alex Jinpeng Wang

Paper Project Code

BrainNetMLP functional brain network classification pipeline

MICCAI-W 2025 BrainNetMLP: An Efficient and Effective Baseline for Functional Brain Network Classification Oral & Best Paper

Jiacheng Hou, Zhenjie Song, Ercan Engin Kuruoglu

Bidirectional Error-Aware Fusion Network architecture

IEEE TCSVT 2025 Bidirectional Error-Aware Fusion Network for Video Inpainting

Jiacheng Hou, Zhong Ji, Jinyu Yang, Feng Zheng

MCD-Net color and depth video-inpainting architecture

IEEE TIP 2024 MCD-Net: Toward RGB-D Video Inpainting in Real-World Scenes

Jiacheng Hou, Zhong Ji, Jinyu Yang, Chengjie Wang, Feng Zheng

Awards & Honors

2026Golden Reviewer, ICML 2026
2025Future Leaders Scholarship, Tsinghua University
2025Best Paper Award (BrainNetMLP), MICCAI Workshop on Efficient Medical AI
2025Outstanding Master’s Thesis, Chinese Institute of Electronics
2024Outstanding Graduate, Tianjin University
2022National Scholarship, Ministry of Education, China

Academic Service

ReviewerICML, NeurIPS, ICLR, IEEE TIP, IEEE TCSVT