Hongzheng Yang | Academic Homepage

Research

Aligning model behavior through explicit control mechanisms

World Models and Generative Control

Training and aligning generative systems with explicit signals for temporal consistency, preference, and controllable behavior.

LLMs and RL Post-Training

Improving reasoning and robustness under noisy supervision through post-training objectives, entropy control, and reward design.

AI Alignment and Reliability

Developing faithful mechanisms for uncertainty calibration, safety concept control, and behavior alignment beyond benchmark accuracy.

Publications

For the most up-to-date list, please see my Google Scholar profile.

2026
Scaling Language Model Reliability via Determinantal Point Process Prompt Sampling Z. Lin, D. Zhu, H. Yang, V. A. Nguyen Preprint, 2026
2026
Concept Concentration for Faithful Representation Intervention H. Yang*, Y. Chen*, Z. Qin, T. Liu, C. Xiao, K. Zhang, B. Han ICML 2026
2026
RSTFA: Efficient Training-Free Human Preference Alignment via Rejection Sampling for Text-to-Image Diffusion Models H. Yang, J. C. L. Li, K. Liu, W. Ma, M. Xu, Y. Zhao, L. M. Po IEEE Transactions on Image Processing, 2026
2025
From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training D. Xu*, H. Yang*, Y. Zhao, P. Zhang, J. Chen, W. Ma, Z. Hou, M. Wu, X. Li, S. Hu, Z. Guan, J. C. L. Li, L. M. Po CVPR 2026
2023
Uncertainty Estimation for Safety-Critical Scene Segmentation via Fine-Grained Reward Maximization H. Yang*, C. Chen*, Y. Chen, H. C. Yip, Q. Dou NeurIPS 2023
2022
DLTTA: Dynamic Learning Rate for Test-Time Adaptation on Cross-Domain Medical Images H. Yang, C. Chen, M. Jiang, Q. Liu, J. Cao, P. A. Heng, Q. Dou IEEE Transactions on Medical Imaging, 2022

2026
Scaling Language Model Reliability via Determinantal Point Process Prompt Sampling Z. Lin, D. Zhu, H. Yang, V. A. Nguyen Preprint, 2026
2026
Concept Concentration for Faithful Representation Intervention H. Yang, Y. Chen, Z. Qin, T. Liu, C. Xiao, K. Zhang, B. Han ICML 2026
2026
RSTFA: Efficient Training-Free Human Preference Alignment via Rejection Sampling for Text-to-Image Diffusion Models H. Yang, J. C. L. Li, K. Liu, W. Ma, M. Xu, Y. Zhao, L. M. Po IEEE Transactions on Image Processing, 2026
2026
VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language Models M. Xu, J. Chen, Y. Zhao, J. C. L. Li, Y. Qiu, Z. Du, M. Wu, P. Zhang, K. Li, H. Yang, et al. Proceedings of the AAAI Conference on Artificial Intelligence, 2026
2026
From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training D. Xu*, H. Yang*, Y. Zhao, P. Zhang, J. Chen, W. Ma, Z. Hou, M. Wu, X. Li, S. Hu, Z. Guan, J. C. L. Li, L. M. Po CVPR 2026
2025
AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment K. Li, L. M. Po, H. Yang, X. Xu, K. Liu, Y. Zhao EMNLP 2025
2025
SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning J. Chen, R. Cong, Y. Zhao, H. Yang, G. Hu, H. H. S. Ip, S. Kwong ICML 2025
2025
Towards Fair Decentralized Benchmarking of Healthcare AI Algorithms with the Federated Tumor Segmentation Challenge M. Zenk, U. Baid, S. Pati, A. Linardos, B. Edwards, M. Sheller, P. Foley, et al. Nature Communications, 2025
2025
Better Reasoning with Less Data: Enhancing VLMs Through Unified Modality Scoring M. Xu, A. Estornell, H. Yang, Y. Zhao, Z. Zhu, Q. Xuan, J. Wei arXiv preprint arXiv:2506.08429, 2025
2025
Feasibility of Real-Time Artificial Intelligence-Assisted Anatomical Structure Recognition During Endoscopic Submucosal Dissection M. W. Scheppach, H. C. Yip, Y. Chen, H. Yang, J. Cao, T. Chua, Q. Dou, et al. Endoscopy International Open, 2025
2023
Uncertainty Estimation for Safety-Critical Scene Segmentation via Fine-Grained Reward Maximization H. Yang*, C. Chen*, Y. Chen, H. C. Yip, Q. Dou NeurIPS 2023
2023
Intelligent Surgical Workflow Recognition for Endoscopic Submucosal Dissection with Real-Time Animal Study J. Cao, H. C. Yip, Y. Chen, M. Scheppach, X. Luo, H. Yang, M. K. Cheng, Y. Long, et al. Nature Communications, 2023
2023
IOP-FL: Inside-Outside Personalization for Federated Medical Image Segmentation M. Jiang, H. Yang, C. Cheng, Q. Dou IEEE Transactions on Medical Imaging, 2023
2022
DLTTA: Dynamic Learning Rate for Test-Time Adaptation on Cross-Domain Medical Images H. Yang, C. Chen, M. Jiang, Q. Liu, J. Cao, P. A. Heng, Q. Dou IEEE Transactions on Medical Imaging, 2022
2022
Dynamic Bank Learning for Semi-Supervised Federated Image Diagnosis with Class Imbalance M. Jiang, H. Yang, X. Li, Q. Liu, P. A. Heng, Q. Dou MICCAI 2022
2022
Efficient Federated Tumor Segmentation via Parameter Distance Weighted Aggregation and Client Pruning M. Jiang, H. Yang, X. Zhang, S. Zhang, Q. Dou MICCAI BrainLes Workshop, 2022
2021
Federated Semi-Supervised Medical Image Classification via Inter-Client Relation Matching Q. Liu, H. Yang, Q. Dou, P. A. Heng MICCAI 2021
2021
Efficient Federated Tumor Segmentation via Normalized Tensor Aggregation and Client Pruning Y. Yin, H. Yang, Q. Liu, M. Jiang, C. Chen, Q. Dou, P. A. Heng MICCAI BrainLes Workshop, 2021

* indicates equal contribution.

Academic Service

Professional activities

Reviewer: ICML, NeurIPS
Reviewer: ECCV, CVPR
Reviewer: COLM

Recognition

Honors and awards

Champion, MICCAI FeTS Challenge, Generalization "In The Wild" track
Bachelor's Thesis with Distinction
Honor Student Scholarship for all academic years, Beihang University

Teaching

Teaching experience

2023-2024 Fall

Fundamentals of Artificial Intelligence

CSCI 3230 & ESTR 3108

2022-2023 Fall

Fundamentals of Artificial Intelligence

CSCI 3230 & ESTR 3108