Amir Bar

@_amirbar

Assistant Professor @imperialcollege MTS @amilabs

London

amirbar.net

Joined March 2016

1,486 Following

4,197 Followers

Replies Reposts Media

Pinned
Amir Bar
@_amirbar
Jun 15
A triple life update: 1. I recently moved from NYC to London 2. I’m starting a new lab at @imperialcollege 3. I’ve joined my friends and mentors at @amilabs as a founding Member of Technical Staff It's time to build 🏗️🧑‍🍳
90
Amir Bar
@_amirbar
Oct 23
cool. it will be interesting to see in larger scale. Intuitively, we know that random search scales exponentially with the number of parameters whereas sgd is polynomial (for convex objectives).
spicylemonade
@spicey_lemonade
Oct 22
WE DID IT! We can now pretrain transformers without backprop and even beat backprop+Adam on validation loss with insane speeds. Now the big question is scale. It’s Ironic, we have reached a breakthrough In AI capability due to inspiration from a safety blog
Quote
Samip
@industriaalist
Oct 22
I think the last month might have been the biggest month in (zeroth-order) optimization history. In the 10 days since we released the Noise speedrun, the time to pretrain a transformer went from 1.76 hours to 1.6 seconds, a 4,000x (!!!) speedup. Dust itself was up to 10,000x
Amir Bar
@_amirbar
Oct 23
Join Jesse's tutorial if you're attending NeurIPS!
Chieh-Hsin (Jesse) Lai
@JCJesseLai
Oct 22
🎉 Excited to bring our book The Principles of Diffusion Models to @NeurIPSConf 2026 as a tutorial—this time, all about diffusion LLMs! 🚀 🔹 How do ideas from continuous diffusion extend to language generation? 🔹 What are the latest advances and open frontiers in diffusion
Quote
Subham Sahoo
@ssahoo_
Oct 22
🎊 Excited to give a tutorial on diffusion LLMs at @NeurIPSConf 2026 with @StefanoErmon @JCJesseLai @mittu1204 📆 Mon, Dec 7, 9 AM AEDT 📍 TikTok Ent Centre (Sydney, Australia) Topics covered: > A beginner friendly introduction to diffusion-LLMs > Designing frontier
1
Amir Bar
@_amirbar
Oct 8
NAVA-WAM: Can we learn latent actions for World Action Models? We revisit a classic idea: jointly learning inverse and forward dynamics models while avoiding the identity shortcut (e.g., @SeonghyeonYe, @garridoq_, @jeffacce, @pulkitology, and others). The twist: Both models are
Zhaochong An
@ZhaochongAn
Oct 5
🤖 Abundant videos capture how the world works, but robot policies still rely on costly action labels to learn. 🔥 Excited to share our work at @Meta: 📢 Native Action-Prior Learning from Videos for World Action Models 📢 📄arxiv.org/pdf/2610.03391 🌐zhaochongan.github.io/NAVA-WAM/ 🧵
Amir Bar
@_amirbar
Oct 6
𝗣𝗿𝗼𝗪𝗔𝗠 imagines latent visual subgoals to guide action prediction. Strong performance across robotics benchmarks and real-world experiments. 🧵👇
Fei Zhang
@809428184Fei
Oct 5
👋 𝗛𝗲𝗹𝗹𝗼 𝗧𝘄𝗶𝘁𝘁𝗲𝗿! 𝗙𝗶𝗿𝘀𝘁 𝘁𝘄𝗲𝗲𝘁 𝗮𝗹𝗲𝗿𝘁 🚨 Why not give it to a paper! Excited to share our work at @Meta: 𝗣𝗿𝗼𝗪𝗔𝗠 In this paper, we try to answer: "How should a robot imagine the future before it acts?" 🌐 Webpage: sii-ferenas.github.io/ProWAM-page/ 🧵👇
2

Amir Bar

Amir Bar’s posts