正在加载视频...

视频加载失败

Some papers rejected due to "incremental novelty" 🫠 We as a community should emphasize less on being novel and more on being simple, interesting, and useful.

32,129 次观看 • 1 年前 •via X (Twitter)

9 条评论

Andrea Tagliasacchi 🇨🇦 的头像
Andrea Tagliasacchi 🇨🇦1 年前

Also the paper that introduced the concept of entropy by Shannon 😂

CoinTracker 的头像
CoinTracker1 年前

Hi 👋 We look a little different. A bold new brand for a bold new era — but not only that. More on what we’ve been up to…

Sahil Khose 的头像
Sahil Khose1 年前

@fionakryan

lynnette ng 的头像
lynnette ng1 年前

Oh yes! Lucas Kanade was one of the papers that was so simple that changed the field. In fact, Kanade rejected the solution when Lucas first proposed it cuz he thought it couldn’t be that easy.

Satanu Ghosh 的头像
Satanu Ghosh1 年前

Simple and novel are two independent concepts.

Bhaktavaschal Samal 的头像
Bhaktavaschal Samal1 年前

be novel notwithstanding the rejection generation issues maybe coming into play

No thanks honey 的头像
No thanks honey1 年前

Incremental novelty is literally the definition of this 13yo deep learning frenzy. What a pompous bunch that declare they are special...

Hassan Al-Farhan 的头像
Hassan Al-Farhan1 年前

Totally with you. Our community needs to value simplicity and usefulness in research over just chasing novelty. Let's make impactful work a priority.

Kosti 的头像
Kosti1 年前

Sounds like the tagline of @TmlrPub :-)

相关视频