KEMBAR78 | Portal Berita

Yibin Wang

Yibin Wang (王逸彬)

I'm a direct PhD student (2024~2029) at Fudan University in Shanghai, advised by Prof. Cheng Jin and Prof. Weizhong Zhang. Currently, I am enrolled in a joint doctoral training program at the Shanghai Innovation Institute, advised by Jiaqi Wang. I am also mentored by Dr. Yuhang Zang. Now I'm a research intern in the Hunyuan team of Tencent (Qingyun Project).

I graduated as an undergraduate from the College of Computer Science and Technology at Zhejiang University of Technology in 2024, advised by Prof. Jianwei Zheng.

| |

Recent Publications

I am now focused on computer vision, generative AI, and visual-language models. I have experience in AI applications for medical images during my undergraduate.

	Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning Yibin Wang, Zhimin Li, Yuhang Zang, Chunyu Wang, Qinglin Lu, Cheng Jin, Jiaqi Wang. NeurIPS, 2025 project page / arXiv / code
	DreamText: High Fidelity Scene Text Synthesis Yibin Wang, Weizhong Zhang, Honghui Xu, Cheng Jin. CVPR, 2025 project page / arXiv / code
	High-fidelity Person-centric Subject-to-Image Synthesis Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin. CVPR, 2024 paper / arXiv / code
	PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin. ACM MM, 2024 paper / arXiv / code

Selected Preprints

	UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation Yibin Wang, Zhimin Li, Yuhang Zang, Jiazi Bu, Yujie Zhou, Yi Xin, Junjun He, Chunyu Wang, Qinglin Lu, Cheng Jin, Jiaqi Wang. project page / arXiv / code
	Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning Yibin Wang, Zhimin Li, Yuhang Zang, Yujie Zhou, Jiazi Bu, Chunyu Wang, Qinglin Lu, Cheng Jin, Jiaqi Wang. project page / arXiv / Pref-GRPO code / UniGenBench code
	Unified Reward Model for Multimodal Understanding and Generation Yibin Wang, Yuhang Zang, Hao Li, Cheng Jin, Jiaqi Wang. project page / arXiv / code
	LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment Yibin Wang, Zhiyu Tan, Junyan Wang, Xiaomeng Yang, Cheng Jin, Hao Li. project page / arXiv / code
	MagicFace: Training-free Universal-Style Human Image Customized Synthesis Yibin Wang, Weizhong Zhang, Cheng Jin. project page / arXiv / code

Selected Awards

• National Scholarship, 2025 (PhD student)

• Future Star Honor, 2024 (Research intern, Shanghai Academy of AI for Science)

• National Scholarship, 2024 (PhD student)

• National Scholarship, 2023 (undergraduate student)

Other Publications

[1] PLSNet: Position-aware GCN-based autism spectrum disorder diagnosis via FC learning and ROIs sifting.
Yibin Wang, Haixia Long, Qianwei Zhou, Tao Bo, Jianwei Zheng. Computers in Biology and Medicine (SCI Q1, Top), 2023

[2] Nonlinear Learnable Triple-Domain Transform Tensor Nuclear Norm for Hyperspectral Image Super-Resolution
Honghui Xu, Mengjie Qin, Quanyue Qian, Yibin Wang, Chuangjie Fang, Yan Li, Jianwei Zheng. TGRS (SCI Q1, Top, IF: 8.5), 2025

[3] Residual Graph Transformer for Autism Spectrum Disorder Prediction.
Yibin Wang, Haixia Long, Tao Bo, Jianwei Zheng. Computer Methods and Programs in Biomedicine (SCI Q2, Top), 2024

[4] Laboring on less labors: RPCA Paradigm for Pan-sharpening
Honghui Xu, Chuangjie Fang, Yibin Wang, Jie Wu, Jianwei Zheng. ICCV (CCF A), 2025

[5] InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles
Zizhen Li, Chuanhao Li, Yibin Wang, Qi Chen, Diping Song, Yukang Feng, Jianwen Sun, Jiaxin Ai, Fanrui Zhang, Mingzhu Sun, Kaipeng Zhang. EMNLP (Main), 2025

[6] Dynamic Operator Optimization for Efficient Multi-Tenant LoRA Model Serving
Changhai Zhou, Yuhua Zhou, Shiyang Zhang, Yibin Wang, Zekai Liu. AAAI (CCF A), 2025

[7] CA-GAN: Object Placement via Coalescing Attention based Generative Adversarial Network.
Yibin Wang, Yuchao Feng, Jie Wu, Honghui Xu, Jianwei Zheng. ICME, 2023

[8] Learning Object Placement via Convolution Scoring Attention.
Yibin Wang, Yuchao Feng, Jianwei Zheng. BMVC, 2024

[9] Enhancing Object Coherence in Layout-to-Image Synthesis.
Yibin Wang, Changhai Zhou, Honghui Xu. ICME, 2025

Research Experience

	Tencent Hunyuan Topic: Multimodal Reinforcement Learning Shanghai, China Jun. 2025 - Present
	Shanghai AI Lab Topic: Multimodal Reinforcement Learning Mentors: Dr. Jiaqi Wang and Yuhang Zang Shanghai, China Jan. 2025 - Jun. 2025
	Shanghai Academy of AI for Science Topic: Text-to-Video Reinforcement Learning Mentor: Dr. Hao Li Shanghai, China Oct. 2024 - Jan. 2025