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.

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!


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

🚀 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.

🧵👇


Denis Tarasov reposted

🎥 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!

Denis Tarasov reposted

🔥 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!

Denis Tarasov reposted

🔥 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.

Loading...

Something went wrong.


Something went wrong.