I am a Master’s student at University of Michigan, Ann Arbor (Class of 2026), majoring in Electrical and Computer Engineering. My academic journey began at Zhejiang University, where I earned a B.Eng. in Automation.
My research interests broadly span multimodal learning, vision-language understanding, reasoning and generation, and reinforcement learning for foundation models. I am drawn to problems where different modalities (vision, language, structured knowledge) must be jointly understood, aligned, and reasoned over. My recent work explores latent visual reasoning in VLMs and sub-dimensional cross-modal retrieval.
Beyond research, I am an adrenaline enthusiast — a licensed skydiver (USPA A License), CASI Level 2 snowboard instructor, PADI Advanced Open Water freediver, and IKO certified kitesurfer. I also share my life with an Australian Shepherd (八戒) and a Maine Coon (狗蛋儿).
🔔 I am actively seeking PhD positions and research assistant opportunities starting 2026–2027. Feel free to reach out via email or check my CV.
📝 Publications
Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs
Mengdan Zhu*, Senhao Cheng*, Liang Zhao (*Equal Contribution)
Under Review at ACL ARR 2026
- Premise-conditioned latent reasoning with dynamic multi-step visual grounding
- Spherical Gaussian Latent Policy for RL exploration on hyperspherical manifold
- Three-stage pipeline: contrastive pretraining → SFT → reinforcement finetuning
- V* Bench 83.8%, MathVista 67.5%, MMMU-Pro 56.1%, MMStar 65.2%, surpassing GPT-4o
Cross-modal RAG: Sub-dimensional Text-to-Image Retrieval-Augmented Generation
Mengdan Zhu*, Senhao Cheng*, Guangji Bai, Yifei Zhang, Liang Zhao (*Equal Contribution)
Under Review at ACL ARR 2026 | arXiv | Code
- Sub-dimensional dense retriever with lightweight adaptor (0.01× CLIP’s GPU memory)
- Multi-objective Pareto-optimal image selection with theoretical guarantees
- MS-COCO R@1 81.82% (prev. best 59.10%), Flickr30K R@1 97.50%
ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain
Haochen Zhao*, Xiangru Tang*, …, Senhao Cheng, …, Mark Gerstein
- Comprehensive benchmark with 30,000+ samples for evaluating LLM safety in chemistry
- Covers chemical properties, usage legality, and synthesis methods
- Incorporates handcrafted templates and advanced jailbreaking scenarios
A Breast Cancer Detection Model Based on Modified ConvNeXt v2
Senhao Cheng, Esther Sun, Wangzi Qian, Yang Han
Published | DOI
- Modified ConvNeXt v2 with Generalized-Mean Pooling and AdaBelief optimizer
- pF1 improvements of 0.031–0.043 over ResNet50, GoogLeNet, and EfficientNet-B2
📖 Education
- 2024 - 2026, M.S. in Electrical and Computer Engineering, University of Michigan, Ann Arbor
- Focus: Multimodal Reasoning, Vision-Language Models, RL for VLMs
- 2020 - 2024, B.Eng. in Automation, Zhejiang University, Hangzhou, China
💼 Internships
- 2023.09 - 2024.04, AI & Data Analysis Intern, MindRank Ltd., Hangzhou, China
- Knowledge Graph construction, Biomedical Data analysis, Drug Discovery pipeline, Predictive Modeling