Mux

Ph.D. student at Takamichi Lab. (from 2026.4)
Deep Learning / Acoustic / Speech processing / Spatial Audio
Trilingual(English/Japanese/Chinese)

[Mux @_muxxum]

@forthshinji 超敏感超精密機械😂

[Mux @_muxxum]

呜呜呜彪哥被投毒毒死了
我的互联网小狗没有了

[Mux @_muxxum]

Anthropic 就该把他们那个 auto mode classifier 的 idea 拿出来单独做个产品
这不比某新模型 novel？

[Mux @_muxxum]

@0xfufu_d667 不是，这对吗

[Mux @_muxxum]

“宇宙大爆炸开始的 ICLR 的投稿数加起来都没有今年一年多”

真的给我看乐了

[Mux @_muxxum]

就决定是你了！
上吧！

[Shinnosuke Takamichi / 高道 慎之介 @forthshinji]

識別番号のあるポケモン博士，ORCID 博士

[Mux @_muxxum]

ICASSP 延长了一星期？
这尼玛

[Mux @_muxxum]

@luinlee 其实也不是不行，弟子不必不如师

[Mux @_muxxum]

每次在 Slack 上看到博导在一点半发消息
我就在想，他不需要睡觉的吗？我到十点就困得不行了

[Mux @_muxxum]

突然意识到一个问题
我没什么必要用外语去写推文
这叫什么？主体思想（乐）

[Mux @_muxxum]

总之不管是骡子是马
先投给 icassp

[Mux @_muxxum]

很离谱的一个点是
DJI Osmo Pocket 4 Pro 拍摄的视频
双声道下居然还有正儿八经的 panning 调整

[Mux @_muxxum]

这跟老父亲有什么区别

[Mux @_muxxum]

impressive!

[OpenAI @OpenAI]

We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.

The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.

The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.

[Mux @_muxxum]

@pocopoco0000 今日午前中11:15で第7会場で発表します。🙋

[Mux @_muxxum]

冷知识
低体脂的人：
当你感到不耐烦看什么都想发脾气
一般都是因为饿了

[Tyler @rezoundous]

Thank you Tibo for resetting Claude usage limits!

[OpenAI @OpenAI]

This is GPT-6 Astra.

Anything you can do on a computer, Astra can do for you. Fast.

[Mux @_muxxum]

solかFableが使い放題になれば。。。

[Mux @_muxxum]

I'll be presenting our recent work, "Learning Blind Speech Separation and Spatial Propagation via Attention based Graph Neural Network for Spatial Voice Conversion," at the ASJ Autumn Meeting 2026.