Yuhong Dai

About

I am a senior undergraduate majoring in Computer Science at Shenzhen University. I am currently seeking PhD and research internship opportunities in efficient inference for large models. If you are interested, please feel free to email me.

Research Interests

I am interested in context compression for LLM-based agents and next-generation efficient model architectures.

My previous work focused on large model pre-training, efficient inference, and multimodal AI companions.

Publications

* denotes equal contribution. Full list on Google Scholar.

1. 
   ICML 2026 Co-first author

   Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

   W Yan*, Y Dai*, Q Ran, H Li, W Lin, H Liao, X Xie, T Jin, J Lian

   ICML 2026 — Poster
2. 
   ACL 2025 First author

   Pretraining Context Compressor for Large Language Models with Embedding-Based Memory

   Yuhong Dai, Jianxun Lian, Yitian Huang, Wei Zhang, Mingyang Zhou, Mingqi Wu, Xing Xie, Hao Liao

   ACL 2025 (Main Conference)

   code
3. 
   arXiv 2026 First author

   WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics

   Y Dai, Y Lai, M Huang, H Guo, D Li, H Peng, H Li, Y Zhao, H Lyu, Z Ge, et al.

   arXiv:2603.13391

   paper

Experience

StepFun

Beijing, China

Foundation Model Post-training Intern

Worked on reward modeling and RLHF pipelines for Step series models.

Microsoft Research Asia

Beijing, China

Research Intern, Social Computing Group

Star of Tomorrow Award

Tencent

Shenzhen, China

Software Engineering Intern

RoboMaster

China (Dongguan / Changsha / Shenzhen)

Vision Team Member

Developed perception and vision modules for autonomous robotic systems in RoboMaster competitions.