Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation

arXiv'25

VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models

ICML'25

Temporal Regularization Makes Your Video Generator Stronger

arXiv'25

DependEval: Benchmarking LLMs for Repository Dependency Understanding

ACL'25

Text-Visual Semantic Constrained AI-Generated Image Quality Assessment

ACM MM 2025

CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning

ACM MM'24

FineCLIPER: Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs

ACM MM'24

Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding

Porject and Code

Recent Trends of Multimodal Affective Computing: A Survey from NLP Perspective

arXiv'24

Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification

AAAI 2025

GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting

Project and Code

BoViLA: Bootstrapping Video-Language Alignment via LLM-Based Self-Questioning and Answering

Github

Evidential Deep Partial Multi-View Classification With Discount Fusion

arXiv'24

Towards Robust Uncertainty-Aware Incomplete Multi-View Classification

arXiv'24

Adaptive weighted multi-view evidential clustering with feature preference

Knowledge Based System 2024

A belief logarithmic similarity measure based on Dempster-Shafer theory and its application in multi-source data fusion

Github

VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation

Project Page

Previous Next
Haojian Huang (黃浩健)

Haojian Huang
黃浩健

Phd Student, AI Thrust, The Hong Kong University of Science and Technology (Guangzhou)

Do not go gentle into that good night



Biography

Haojian Huang is a PhD student at The Hong Kong University of Science and Technology (GZ), supervised by Prof. Yingcong Chen. His research spans Trusted AI, Embodied AI, and Video Understanding & Generation. He previously interned at TeleAI and Huawei Noah's Ark Lab, collaborating closely with Associate Professor Mulin Chen and Principal Researcher Yinchuan Li. He will join Knowin.ai to deepen his focus on Embodied AI, aiming to build engaging and reliable intelligent systems that advance human well-being. Beyond research, he leads CareerSynapse, a dynamic, student-driven initiative that explores practical applications of agentic AI systems. He welcomes ANY AI research collaboration.


Interests

  • Trusted AI
  • Personalized AGI
  • Video Understanding & Generation
  • Embodied AI

Education

  • MSc in Computer Science, 2024-2025
    Department of Computer Science
  • BSc in Computer Science, 2020-2024
    Department of Computer Science

News

【2025-5-3】One paper is accpted to ICML'25!

2024-12-12
Haojian Huang (黃浩健)
PDF Code

【2024-12-12】Served as a reviewer for ICML'25.

2024-12-12
Haojian Huang (黃浩健)
缩略图

【2024-12-10】One paper is accepted to AAAI 2025！

2024-12-10
Haojian Huang (黃浩健)
Code

【2024-11-14】Served as a reviewer for IEEE Transactions on Image Processing.

2024-11-15
Haojian Huang (黃浩健)
缩略图

【2024-11】Work as an intern in NOAH'S ARK LAB in HUAWEI !!!

2024-11-01
Haojian Huang (黃浩健)
缩略图

【2024-10-30】Served as a reviewer for TAFFC.

2024-10-30
Haojian Huang (黃浩健)
缩略图

【2024-09-09】Served as a reviewer for ICLR'25.

2024-09-09
Haojian Huang (黃浩健)
缩略图

【2024-07-16】Two papers are accepted to ACM MM 2024!

2024-07-16
Haojian Huang (黃浩健)
Code Project

【2024-06-21】One paper is accepted to Knowledge-Based Systems 2024!

Multi-view clustering has attracted substantial attention thanks to its ability to integrate informa···
2024-06-21
Haojian Huang (黃浩健)
Project
缩略图

【2024-05-23】Served as a reviewer for NeurIPS'24.

2024-05-23
Haojian Huang (黃浩健)
缩略图

Recent Publications & Preprints

Harold Haodong Chen, Haojian Huang, Qifeng Chen, Harry Yang, Ser-Nam Lim Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation (arXiv 2025)
L2-regularization based two-way weighted neutrosophic clustering with Manhattan and Euclidean distances L2-regularization based two-way weighted neutrosophic clustering with Manhattan and Euclidean distances (FSS 2025)
Qiang Li, Qingsen Yan, Haojian Huang, Peng Wu, Haokui Zhang, Yanning Zhang Text-Visual Semantic Constrained AI-Generated Image Quality Assessment (ACM MM 2025)
Haojian Huang, Haodong Chen, Shengqiong Wu, Meng Luo, Jinlan Fu, Xinya Du, Hanwang Zhang, Hao Fei VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models (ICML 2025)
Junjia Du, Yadi Liu, Hongcheng Guo, Jiawei Wang, Haojian Huang, Yunyi Ni, Zhoujun Li. DependEval: Benchmarking LLMs for Repository Dependency Understanding (ACL Findings 2025)
Harold Haodong Chen, Haojian Huang, Xianfeng Wu, Yexin Liu, Yajing Bai, Wen-Jie Shu, Harry Yang, Ser-Nam Lim. Temporal Regularization Makes Your Video Generator Stronger (arxiv 2025)
Haojian Huang, Chuanyu Qin, Zhe Liu, Kaijing Ma, Jin Chen, Han Fang, Chao Ban, Hao Sun, Zhongjiang He. Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification (AAAI 2025)
Mingzhe Zheng, Yongqi Xu, Haojian Huang, Xuran Ma, Yexin Liu, Wenjie Shu, Yatian Pang, Feilong Tang, Qifeng Chen, Harry Yang, Ser-Nam Lim. VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation (arXiv 2024)
Jin Chen, Kaijing Ma, Haojian Huang, Jiayu Shen, Han Fang, Xianghao Zang, Chao Ban, Zhongjiang He, Hao Sun, Yanmei Kang. BoViLA: Bootstrapping Video-Language Alignment via LLM-Based Self-Questioning and Answering (arXiv 2024).
Guimin Hu, Yi Xin, Weimin Lyu, Haojian Huang, Chang Sun, Zhihong Zhu, Lin Gui, Ruichu Cai, Erik Cambria, Hasti Seifi Recent Trends of Multimodal Affective Computing: A Survey from NLP Perspective (arxiv 2024).
Haojian Huang, Xiaozhen Qiao, Zhuo Chen, Haodong Chen, Bingyu Li, Zhe Sun, Mulin Chen, Xuelong Li. CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning (ACM MM 2024).
Haodong Chen, Haojian Huang, Junhao Dong, Mingzhe Zheng, Dian Shao. Finecliper: Multi-modal fine-grained clip for dynamic facial expression recognition with adapters (ACM MM 2024).
Kaijing Ma, Haojian Huang, Jin Chen, Haodong Chen, Pengliang Ji, Xianghao Zang, Han Fang, Chao Ban, Hao Sun, Mulin Chen, Xuelong Li. Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding (arXiv 2024).
Haojian Huang, Zhe Liu, Sukumar Letchmunan, Muhammet Deveci, Mingwei Lin, Weizhong Wang. Evidential Deep Partial Multi-View Classification With Discount Fusion (arXiv 2024).
Zhe Liu, Haojian Huang, Sukumar Letchmunan, Muhammet Deveci. Adaptive weighted multi-view evidential clustering with feature preference (Knowledge-Based Systems 2023).
Haodong Chen, Yongle Huang, Haojian Huang, Xiangsheng Ge, Dian Shao. GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting (arXiv 2024)
Zhe Liu, Haojian Huang, Sukumar Letchmunan. Adaptive weighted multi-view evidential clustering (ICANN 2023)
Zhe Liu, Haojian Huang. Comment on “new cosine similarity and distance measures for fermatean fuzzy sets and topsis approach” (Knowledge and Information Systems, 2023)
Haojian Huang, Zhe Liu, Xue Han, Xiangli Yang, Lusi Liu. A belief logarithmic similarity measure based on dempster-shafer theory and its application in multi-source data fusion (Journal of Intelligent & Fuzzy Systems 2023)

CareerSynapse

Leader

Avatar

Haojian Huang

Phd Student, AI Thrust, The Hong Kong University of Science and Technology (Guangzhou)

Advisory Committee

Avatar

Haodong Chen

Undergrad., School of Automation, Northwestern Polytechnical University

Avatar

Xiaozhen Qiao

Ph.D Student, School of Information Science and Technology, University of Science and Technology of China

Avatar

Zhe Liu

Researcher, School of Computer Science, Universiti Sains Malaysia

Avatar

Zili Zou

Master Student, Department of Electronic Engineering, Tsinghua University

Avatar

Jin Chen

Master Student, School of Mathematics and Statistics, Xi’an Jiaotong University

Avatar

Kaijing Ma

Master Student, Faculty of Electronic and Information Engineering, Xi’an Jiaotong University

Avatar

Chuanyu Qin

Master Student, Computer Science, Institute of Information Engineering，Chinese Academy of Sciences

Developers

Projects

*
All Video Trusted AI Face Analyses Personalized AGI Embodied AI

VistaDPO

Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models

VIDEO GENERATION MODEL TEMPORAL SSL

Temporal Regularization Makes Your Video Generator Stronger

VIDEO TEMPORAL GROUNDING

Evidential Deep Learning for Robust Video Temporal Grounding

DYNAMIC FACIAL EXPRESSION RECOGNITION

Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs

VIDEO Question Answering

VideoGen-of-Thought

A Collaborative Framework for Multi-Shot Video Generation

DependEval

DependEval: Benchmarking LLMs for Repository Dependency Understanding

VIDEO TEMPORAL GROUNDING

Evidential Deep Learning for Robust Video Temporal Grounding

CREST

Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning

TUNED

Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification

PARTIAL MULTI-VIEW CLASSIFICATION

Evidential Deep Partial Multi-View Classification With Discount Fusion

PARTIAL MULTI-VIEW CLASSIFICATION

Towards Robust Uncertainty-Aware Incomplete Multi-View Classification

DYNAMIC FACIAL EXPRESSION RECOGNITION

Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs

MULTIMODAL AFFECTIVE COMPUTING

Recent Trends of Multimodal Affective Computing: A Survey from NLP Perspective

GaussianVTON

3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting

Contact

  • (+86) 13128232363
  • AI Thrust, The Hong Kong University of Science and Technology (GZ), No. 1 Duxue Road, Nansha District, Guangzhou, Guangdong 511458, P. R. China
一键仿站工具