peryaudo's profile picture. train as many neural nets as possible 🚀

ぺりゃ🚗

@peryaudo

train as many neural nets as possible 🚀

Joined May 2010
Similar User
semiexp's profile picture. ソフトウェアエンジニア | 競プロ / パズル(解く, 作る, プログラミング) / 同人音楽 / DTM / おえかき始めました

@semiexp

namonakiaccount's profile picture. スマホにしたのでツイ廃にならないよう気を付けたい/昔は競プロとかやってたりしました/topcoder:namonakiacc(赤) codeforces:namonakiaccount IOI2015(金)/IOI2016(銀)

@namonakiaccount

Respect2D's profile picture. アイマス好きでたまに山登ります。
Threadsとかhttps://t.co/yG5XmNLXt6とかBlueskyとか、itohjamでやってます。

@Respect2D

hogeover30's profile picture. FF外から失礼されるのは構わないけど「FF外から失礼します」って言われるのは嫌い 
https://t.co/JcOGLTuJxX

@hogeover30

pepsin_amylase's profile picture. Software Engineer @MonoxerJP ex-@indeed, Codeforces Grandmaster, Lord of Sealand, Created AtCoder Problems difficulty estimates. VF19.1

@pepsin_amylase

hirose_golf's profile picture. 主にコンピューター関係のことについて書きます

@hirose_golf

akensho's profile picture. AtCoder / アイコンは千務三さんに描いてもらいました

@akensho

kawatea03's profile picture. 某社で働くソフトウェアエンジニア。プロコンとボードゲームが好きなIS2011er・CS2013er。

@kawatea03

eomole's profile picture. つぶやきはいつだっていみふです。

@eomole

kyuridenamida's profile picture. 最近はValorantにハマっていましたが、あまりにも社会性を失ったのでやめていましたが抗えず再開しましたがまたやめようとしていましたが、子供が生まれ強制的にやめさせてくれたと思ったら思いの外すやすや寝てるのでちょいちょいやってます。ごめん。昔は競技プログラミングやってました。

@kyuridenamida

okaduki's profile picture. 街の国際バリスタえんじにゃぁ(予定)

@okaduki

ir5's profile picture. かっこかわいい小動物が好き
Blog: https://t.co/SF7zfkkCX8

@ir5

shora_kujira16's profile picture. Web系のクラウド基盤エンジニア。競プロと機械学習をやっていました。ICPC OB/OGの会のスタッフ

@shora_kujira16

Mi_Sawa's profile picture. フローが好きだけど, 好かれてはいない.

@Mi_Sawa

__math's profile picture. 競技プログラミング(math, __math) ICPC 2016 World Final (team chikOkU), CTF, ISUCON(team takedashi) splatoon1カンスト, splatoon2: S+200

@__math

ぺりゃ🚗 Reposted

Whoa, this is Temporal Gaussian Hierarchy (TGH). This AI can real-time render long volumetric videos in 1080p at 450 fps on a single RTX 4090 GPU. And 18,000 frames (around 10 minutes) long 🤯 7 wild demos: 1. Real-time demos on MobileStage dataset


ぺりゃ🚗 Reposted

Yall heard it from the man himself

_jasonwei's tweet image. Yall heard it from the man himself

Ilya is here!!!

peryaudo's tweet image. Ilya is here!!!
peryaudo's tweet image. Ilya is here!!!

ぺりゃ🚗 Reposted

🚀 Introducing the Byte Latent Transformer (BLT) – An LLM architecture that scales better than Llama 3 using byte-patches instead of tokens 🤯 Paper 📄 dl.fbaipublicfiles.com/blt/BLT__Patch… Code 🛠️ github.com/facebookresear…

ArtidoroPagnoni's tweet image. 🚀 Introducing the Byte Latent Transformer (BLT) – An LLM architecture that scales better than Llama 3 using byte-patches instead of tokens 🤯 

Paper 📄 dl.fbaipublicfiles.com/blt/BLT__Patch…
Code 🛠️ github.com/facebookresear…

ぺりゃ🚗 Reposted

Waymo's market share is now equal to Lyft within SF. Incredible. Network effects is one of the best sources of defensibility. But it's proven to be not that important in ridesharing. You need a minimum network size, but once you have that, there are diminishing returns. In…

aleximm's tweet image. Waymo's market share is now equal to Lyft within SF. Incredible.

Network effects is one of the best sources of defensibility. But it's proven to be not that important in ridesharing. 

You need a minimum network size, but once you have that, there are diminishing returns. In…

ぺりゃ🚗 Reposted

NASDAQ! Coincheck!

wadakooo's tweet image. NASDAQ!
Coincheck!

学会って大学生の集まりだって忘れてたわ

peryaudo's tweet image. 学会って大学生の集まりだって忘れてたわ

ぺりゃ🚗 Reposted

In case it was unclear before, it is clear now: GM are a bunch of dummies.


ぺりゃ🚗 Reposted

A new tutorial on RL by Kevin Patrick Murphy, a Research Scientist at Google DeepMind who also wrote several comprehensive, well-regarded textbooks on ML/DL. This ought to be a good read 👀

iScienceLuvr's tweet image. A new tutorial on RL by Kevin Patrick Murphy, a Research Scientist at Google DeepMind who also wrote several comprehensive, well-regarded textbooks on ML/DL.

This ought to be a good read 👀

NeurIPSなう


ぺりゃ🚗 Reposted

The inventors of flow matching have released a comprehensive guide going over the math & code of flow matching! Also covers variants like non-Euclidean & discrete flow matching. A PyTorch library is also released with this guide! This looks like a very good read! 🔥

iScienceLuvr's tweet image. The inventors of flow matching have released a comprehensive guide going over the math & code of flow matching!

Also covers variants like non-Euclidean & discrete flow matching.

A PyTorch library is also released with this guide!

This looks like a very good read! 🔥

ぺりゃ🚗 Reposted

I am happy to announce that the first draft of my RL tutorial is now available. arxiv.org/abs/2412.05265

sirbayes's tweet image. I am happy to announce that the first draft of my RL tutorial is now available.
arxiv.org/abs/2412.05265

ブルーレイってジャバを巡る争いだったって知らなかった

peryaudo's tweet image. ブルーレイってジャバを巡る争いだったって知らなかった

ぺりゃ🚗 Reposted

何この人… →留学時代に旅行した南アのソウェト。薄暗い時間帯に十数人の青年に囲まれました。うち数人はナイフを持っている。少林寺拳法の演武を、大声を発しながらやったら相手がひるんだ。全力疾走で20分間くらい走って逃げて命拾いしました アジア開銀総裁 神田真人 nikkei.com/article/DGKKZO…


ぺりゃ🚗 Reposted

OpenAI has added support for RLHF finetuning of their models!

iScienceLuvr's tweet image. OpenAI has added support for RLHF finetuning of their models!

AIって人よりも賢くないけど人より安いから使うものかと思ってたけど、人より賢いから人より高いけど使う物になる日も近そう(?)


ぺりゃ🚗 Reposted

Welcome PaliGemma 2! 🤗 Google released PaliGemma 2, best vision language model family that comes in various sizes: 3B, 10B, 28B, based on Gemma 2 and SigLIP, comes with transformers support day-0 🎁 Saying this model is amazing would be an understatement, keep reading ✨

mervenoyann's tweet image. Welcome PaliGemma 2! 🤗

Google released PaliGemma 2, best vision language model family that comes in various sizes: 3B, 10B, 28B, based on Gemma 2 and SigLIP, comes with transformers support day-0 🎁

Saying this model is amazing would be an understatement, keep reading  ✨

ぺりゃ🚗 Reposted

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →…


ぺりゃ🚗 Reposted

Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Depth without Video Models,” delivers exactly that, setting new standards in temporal consistency. Check out more details in the thread 🧵


Loading...

Something went wrong.


Something went wrong.