English
English Indonesia Türkçe Deutsch Español Português Pусский Français Italiano Nederlands Polski العربية ไทย Tiếng Việt 繁體中文 简体中文 日本語 한국어
ML_is_overhyped's profile picture. Master student and researcher at ETH Zurich. Ex Meta, InstaDeep, JetBrains, Yandex, Tinkoff.

Denis Tarasov

@ML_is_overhyped

Master student and researcher at ETH Zurich. Ex Meta, InstaDeep, JetBrains, Yandex, Tinkoff.

35Posts 177Followers 169Following
You might like
ML_is_overhyped's profile picture.
Denis Tarasov
 @ML_is_overhyped
Oct 13

Don’t want to spam your feeds, but I’m incredibly thankful to the AI community for all the feedback and support on my last tweet. I didn’t expect so many responses -- really happy to be part of such a brilliant community. Thank you so, so much!

0
0
9
2
1K
ML_is_overhyped's profile picture.
Denis Tarasov
 @ML_is_overhyped
Jun 2

I have a strange tradition to work on LM + RL project once a year😶‍🌫️

vladkurenkov's profile picture. honcho @ https://t.co/a5Krlqpeiw
Vladislav Kurenkov
@vladkurenkov
Jun 2

🚀 Introducing cadrille: a new SOTA model for CAD reconstruction from images, point clouds, and text—all in one framework with the use of RLVR. Multimodal inputs + RLVR = clean, editable 3D models. 🧵👇

vladkurenkov's tweet image. 🚀 Introducing cadrille: a new SOTA model for CAD reconstruction from images, point clouds, and text—all in one framework with the use of RLVR. Multimodal inputs + RLVR = clean, editable 3D models. 🧵👇
1
7
19
6
2K
0
0
10
2
1K
Denis Tarasov reposted
how_uhh's profile picture.
Alexander Nikulin
 @how_uhh
May 27

🎥 Pre-training VLAs on human videos is tempting — Latent Action Models quickly become an essential part of leading VLAs, like GR00T (@DrJimFan) — but can they effectively handle messy real‐world videos? In our #ICML paper we give an answer: not yet, at least without some help!

how_uhh's tweet image. 🎥 Pre-training VLAs on human videos is tempting — Latent Action Models quickly become an essential part of leading VLAs, like GR00T (@DrJimFan) — but can they effectively handle messy real‐world videos? In our #ICML paper we give an answer: not yet, at least without some help!
1
26
190
99
13K
Denis Tarasov reposted
max_nygma's profile picture.
Maksim Zhdanov
 @max_nygma
May 26

🔥 Φ-Module 🔥 We present Φ-Module - an easy way to compute partial charges and electrostatic energy in a self-supervised way for any neural network interatomic potential. Learn more below!

max_nygma's tweet image. 🔥 Φ-Module 🔥 We present Φ-Module - an easy way to compute partial charges and electrostatic energy in a self-supervised way for any neural network interatomic potential. Learn more below!
1
4
9
1
2K
Denis Tarasov reposted
suessmannn's profile picture.
Ilya Zisman
 @suessmannn
May 23

🔥 Zero-shot generalization is the dream: adapt instantly, no fine-tuning. It's why LLMs blew up—but it's not just a language modeling thing. It’s happening in RL too. 🚨 @maxsbob21's new paper dives deep into zero-shot RL under shifting dynamics—and why current methods break.

suessmannn's tweet image. 🔥 Zero-shot generalization is the dream: adapt instantly, no fine-tuning. It's why LLMs blew up—but it's not just a language modeling thing. It’s happening in RL too. 🚨 @maxsbob21's new paper dives deep into zero-shot RL under shifting dynamics—and why current methods break.
4
19
142
105
14K

United States Trends

You might like

Something went wrong.


Something went wrong.