• I am currently a fourth-year Ph.D. candidate at Shanghai Jiao Tong University and Shanghai AI Laboratory.
• My research interests include computer vision and music generation, especially for vision language models.
• You can contact me via wangzhaokai [at] sjtu [dot] edu [dot] cn.
• Homepage

一些仓库介绍

• 发表论文

  • CNMT: [AAAI 2021] Confidence-aware Non-repetitive Multimodal Transformers for TextCaps
  • CMT: [ACM MM 2021 Best Paper Award] Video Background Music Generation with Controllable Music Transformer
  • SymMV: [ICCV 2023] Video Background Music Generation: Dataset, Method and Evaluation
  • PIIP: [NeurIPS 2024 Spotlight] Parameter-Inverted Image Pyramid Networks
  • ITINERA: [EMNLP 2024 Industry Track & KDD UrbComp 2024 Best Paper Award] Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning
  • Mono-InternVL: [CVPR 2025] Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training
  • Awesome-Vision-to-Music-Generation: [ISMIR 2025] Vision-to-Music Generation: A Survey
  • VMB: Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation

• 研究笔记

  • COCO-leaderboard：COCO目标检测leaderboard笔记

• 有趣的游戏和工具

  • Sanguosha：文字版三国杀
  • GPT-turtlesoup：ChatGPT实现AI海龟汤，GPT出题、当玩家、当裁判
  • Scraper：小红书、微信公众号、马蜂窝爬虫
  • Pokemon-Types-PageRank：宝可梦属性排名，使用PageRank算法
  • wordle-solver：wordle游戏求解器
  • HRM-architecture：基于人力资源机器游戏的CPU、编译器等架构设计
  • wzk-Game-Collection：python小游戏全集，飞行棋、扫雷、德州扑克、2048、五子棋等
  • Arxiv-Assistant: 自动获取每日的arxiv新论文列表、使用GPT筛选、发邮件提醒
  • luna：简单的版本管理系统
  • hahaha：自动生成表情包
  • wzk-pypi-package：自己的python包，小游戏、爬虫等娱乐性质代码合集

• 大学课程相关

  • BUAA-CS-course-notes：北航计算机专业课代码及期末复习笔记，包含很多课的代码
  • BUAA-getscore：北航查分小工具
  • PhysicsExperiment：基物实验数据计算程序
  • pku-nsd-double-major：北大国发院经双课程复习资料