Hi there!😊 I’m Kairan Dou, welcome to my personal website! Feel free to just call me Kevin. I am a junior undergraduate student majoring in Computer Science at Nankai University, currently an exchange student in the University of California, Berkeley. Since February 2025, I have been a Research Assistant at The University of Texas at Austin, working under the guidance of Prof. Philipp Krähenbühl, focusing on multimodal learning. Previously, I have conducted extensive research at the Visual Computing and Intelligent Perception(VCIP) Lab under the guidance of Prof. Xiang Li.

My current research interests lie in:

  • Reinforcement learning for stability and alignment in VLA models
  • RL-augmented language model search and semantic retrieval
  • Enhancing few-shot and zero-shot generalization in embodied agents

My broader goal is to establish scalable, unified post-training frameworks for embodied multi-modal agents, enabling both fine-grained reasoning and embodied decision-making through unified learning signals.

If you would like to connect further, feel free to contact me via email.

You can also reach me on WeChat at: Darkeyes-

🔥 News

  • 2025.05:  🎉🎉 I finished my new paper.
  • 2025.02:  🎉🎉 I delivered an oral presentation at AAAI 2025 in Philadelphia.
  • 2025.01:  🎉🎉 I arrived in Berkeley and commenced my exchange program.
  • 2024.12:  🎉🎉 Our paper was accepted at AAAI 2025.

📝 Publications

AAAI 2025
sym

From Words to Worth: Newborn Article Impact Prediction with LLM

Penghai Zhao, Xinghua Xing, Kairan Dou, Jinyu Tian, Ying Tai, Jian Yang, Ming-Ming Cheng, Xiang Li

  • Proposed the “Newborn Article Impact Prediction” (Newborn AIP) task and introduced the TNCSIsp metric, achieving an NDCG@20 score of 0.901.
  • Constructed TKPD and NAID datasets, including over 12,000 samples for training and validation.
  • Used LoRA to fine-tune and test 5+ large language models on server to evaluate prediction performance.
  • Authored and finalized sections of the paper, ensuring academic writing standards.

📖 Educations

  • 09/2022-06/2026, B.Eng. in Computer Science, Nankai University.
  • 01/2025-05/2025, Exchange Student, University of California, Berkeley.

💻 Internships

  • 2025.02 - present, Research Assistant, The University of Texas at Austin, United States.
  • 2024.06 - 2025.02, VCIP Lab, Nankai University, China.
  • 2024.06 - 2024.09, Chinasoft International Co., Ltd., China.

💬 Projects

sym

JobForce.AI

LLM-Powered Multi-Agent Platform for Job Seekers

Kairan Dou, Mingxi Tang , Yiya You, Yufeng Yan

  • End-to-end LLM-powered pipeline automates both resume rewriting and job matching in a single workflow.
  • Context-aware resume optimization tailors each experience using representative job descriptions and LLM-generated language.
  • Semantic embedding–driven selection ranks and condenses content based on normalized cosine similarity for maximum relevance.
  • Real-time, personalized job recommendations match optimized resumes against live postings filtered by user preferences.
  • Quantitative alignment evaluation delivers a clear 100-point score and visual feedback on resume–JD fit improvements.
  • 2024.06 - 2025.02, Development of the AI for Research Service App, an automated arXiv paper selection platform that utilizes algorithms to provide users with the latest curated arXiv paper summaries and explanations.
  • 2024.11, Developed agent using retrieval-augmented generation system for detecting and evaluating open-source code in arXiv papers, leveraging GitHub APIs and abstract syntax tree similarity algorithms. <!– - 2024.10, Agent-based technology for automatic author disambiguation and information generation.

🎖 Honors and Awards

  • 2024.08 Awarded Outstanding Individual for contributions to Chinasoft International Co., Ltd.
  • 2024.02 Honorable Mention, Mathematical Contest in Modeling (MCM) –>

💡 Patents

  • Patent pending: Agent-based retrieval-augmented generation system for detecting and evaluating open-source code in arXiv papers, utilizing GitHub APIs and abstract syntax tree similarity algorithms.

🏃‍♂️ Hobbies

  • 🏸 Badminton: Played for approximately five years; member of the college team.​
  • 🎸 Guitar: Served as the vice president of the Guitar Club.​
  • 🎤 Singing: Recognized as one of the top ten singers in the college.​