Rui Huang

B.Eng. Student in Computer Science
Everest Project, University of Electronic Science and Technology of China
Rui Huang portrait

Biography

I am a third-year undergraduate student in the Everest Project Computer Top-Talent Experimental Class at UESTC (2023–2027), majoring in Computer Science (ranked 1/164 in major). I am currently a research intern at Tencent Hunyuan, working with Tianyu Pang on Multimodal Reinforcement Learning. My research interests are Multimodal RL, Agentic AI, and World Models. Earlier, I also worked on AI for smart grids and remote-sensing image fusion.

👋 If you're interested in my research or just want to chat, feel free to reach out by email or .

News

  • 2026/04 Released ClawMark — a living-world benchmark for multi-day, multimodal coworker agents.
  • 2026/02 Two papers D²C and L²P accepted to CVPR 2026.
  • 2025/11 Released P1 — gold-medal-level performance on the International Physics Olympiad (IPhO), beating Gemini 2.5 Pro, GPT-5, and Grok 4. Blog.
  • 2025/11 Released UniVA — an open-source agentic framework that unifies video understanding, editing, and generation. Paper. Reported by AK. 466
  • 2025/11 One paper accepted to IEEE Transactions on Industrial Informatics (SCI Q1).
  • 2025/10 Awarded the National Scholarship 2025.
  • 2025/06 Awarded the SenseTime Scholarship 2025 (30 undergraduates nationwide).
  • 2025/06 One paper accepted to IEEE Transactions on Industrial Informatics (SCI Q1).
  • 2025/03 Released CoT-Image, the first work introducing chain-of-thought-style strategies into image generation. 862
  • 2024/12 One paper WFANet accepted to AAAI 2025 and selected for Oral Presentation.
  • 2024/10 Awarded the National Scholarship 2024 and the Gratitude Scholarship for Modern Scientists.
  • 2024/09 One paper accepted to IEEE Transactions on Sustainable Energy (SCI Q1).
  • 2023/12 Started my academic journey.

Experience

Selected Publications

(* equal contribution  ·  † corresponding author  ·  ‡ project leader)    Full list on Google Scholar

Diffusion Dataset Condensation: Training Your Diffusion Model Faster with Less Data
CVPR 2026
Rui Huang*, Shitong Shao*, Zikai Zhou, Pukun Zhao, Hangyu Guo, Tian Ye, Lichen Bai, Shuo Yang, Zeke Xie†
Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
CVPR 2026
Zhirong Shen*, Rui Huang*‡, Jiacheng Liu, Chang Zou, Peiliang Cai, Shikang Zheng, Zhengyi Shi, Liang Feng, Linfeng Zhang†
Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening
AAAI 2025 Oral
Jie Huang*, Rui Huang*, Jinghao Xu, Siran Peng, Yule Duan, Liangjian Deng†
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
arXiv 2025
Ziyu Guo*, Renrui Zhang*‡†, Chengzhuo Tong*, Zhizheng Zhao*, Rui Huang, Haoquan Zhang, Manyuan Zhang, Jiaming Liu, Shanghang Zhang, Peng Gao, Hongsheng Li†, Pheng-Ann Heng
UniVA: Universal Video Agents towards Next-Generation Video Intelligence
arXiv 2025
Zhengyang Liang*, Daoan Zhang*, Huichi Zhou, Rui Huang, Bobo Li, Shengqiong Wu, Yuechen Zhang, Xiaohan Wang, Jiebo Luo, Lizi Liao, Hao Fei†
P1: Mastering Physics Olympiads with Reinforcement Learning
Tech Report
Jiacheng Chen*, Qianjia Cheng*, Fangchen Yu* … Rui Huang … Lei Bai†, Yu Cheng†, Ning Ding†, Bowen Zhou†, Peng Ye†, Ganqu Cui†
P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads
Tech Report
Yun Luo*†, Futing Wang*, Qianjia Cheng* … Rui Huang … Lei Bai, Yu Cheng, Ning Ding, Bowen Zhou, Peng Ye, Ganqu Cui†
Complementary Online Learning Network for Probabilistic Load Forecasting Against Extreme Weather
IEEE Transactions on Industrial Informatics SCI Q1 · IF 10.2
Rui Huang, Pengfei Zhao, Di Cao†, Weihao Hu, Qi Huang, Zhe Chen

Education

Selected Honors & Awards

Competition Awards

  • National Gold Award National College Student Career Planning Competition · award rate < 0.1% · first from UESTC
    2025
  • National Silver Award China International College Students' Innovation Competition
    2025
  • Provincial Special Prize "Challenge Cup" National College Students' Extracurricular Academic and Technological Works Competition
    2025

Services

WeChat QR code — scan to add me