Skip to content
View chaos7857's full-sized avatar
🍀
Passion is the reason and answer for everything!
🍀
Passion is the reason and answer for everything!

Block or report chaos7857

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 250 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
chaos7857/README.md

Hi there 👋

🤔 About me

Undergraduate student passionate about neural network algorithms.

To make an AI that composes poems and paints work like a beast of burden

😄 Projects

内容正在补全完善中(由于许多都是边学边做的,总结意识不是很强)

LR

具身 仿真 数据分析 真机实验 真机实验 真机实验
nanoGPT 百年孤独
目标检测
HFUT校门三维重建
nerf + 3dgs
评论爬取 + 销量预测
diffusion + 知识图谱 + 推荐系统 123
stable diffusion 图像生成 123

Web

JavaSpring后端 + Vue3 校园周边美食分享系统
Nodejs后端 + Vue3 +微信小程序 辅学系统 123
JavaSpring后端 + ReactNative 日常工具APP 123

Pinned Loading

  1. videoMetaAction videoMetaAction Public

    提出一种新的具身智能思路实现,将具备视频特征预测训练、新的动作扩散思路,以及我心心念念的元动作分解。人工智能领域存在着著名的莫拉维克悖论(Moravec's paradox):高级推理功能反而容易(例如围棋、数学题),下层的感知和执行反而困难(例如各种家务)。VLM 更擅长高层级的推理,而 AIGC 生成式模型更擅长细节处理。

    1