rohan anil (@_arohan

rohan anil

10.6K posts

rohan anil

@_arohan_

member of technical staff & co-founder of @coreautoai - and continuing to aspire to understand deep learning.

Joined December 2017

Pinned
rohan anil
@_arohan_
Apr 19
It turns out multi step backpropaganda is better. paper has a beautiful way of improving backpropagation. One iteration cleanly gets us backprop, multiple iterations get us a preconditioned update.
rohan anil
@_arohan_
Apr 19
Replying to @LinYorker @ryu0000000001 and @weijie444
arxiv.org/abs/2106.06199 Same update here
111K
rohan anil
@_arohan_
Jun 5, 2025
A little bit of update from me: I will join the awesome team at @AnthropicAI in two weeks.
147K
rohan anil
@_arohan_
Jun 5, 2025
93K
rohan anil
@_arohan_
Jan 13, 2025
Joining the Llama team @AIatMeta today! Time to train models, finally gpu rich :)
91K
rohan anil
@_arohan_
Nov 6, 2025
Near the office. SF has stepped up its dosa game.
82K
rohan anil
@_arohan_
Dec 7, 2022
This paper looks like a big step forward for the Transformer architecture! A foundational improvements, not as shiny as other things, but really big step forward nonetheless
rohan anil
@_arohan_
Nov 10, 2025
Reading this, its clear that Meta is advancing / recommender systems tech faster than other places including G.
Engineering at Meta
@Meta_Engineers
Nov 10, 2025
We’re excited to share details on Meta’s Generative Ads Recommendation Model (GEM), a new foundational model built with LLM-scale techniques that’s already helping create more value for businesses, like +5% increase in ad conversions on Instagram. Dive deep into the technology
174K
rohan anil
@_arohan_
Dec 21, 2024
Man, claude solved this verbally by looking at the inputs visually.
François Chollet
@fchollet
Dec 20, 2024
Replying to @fchollet
It will also be extremely important to analyze the strengths and limitations of the new system. Here are some examples of tasks that o3 couldn't solve on high-compute settings (even as it was generating millions of CoT search tokens and consuming thousands of dollars of compute
96K
rohan anil
@_arohan_
Dec 6, 2024
A bitter sweet moment for me, Gemini is doing really well, and teams are doing great. I had a great close to 12 years at G that one could call me OG. For example, for every search query, I noticed things I was able to contribute to is deeply integrated from the retriever to the
83K
rohan anil
@_arohan_
Sep 16, 2023
Meta researchers just dropped PyTorch distributed shampoo🧴few days ago: arxiv.org/pdf/2309.06497… 💥 Train neural networks with a second order method for better performance. This underlying work which it is based on has been a passion project for last 5 years while swimming
113K
rohan anil
@_arohan_
Oct 11, 2025
That’s insane to convince a cofounder of thinky to bail this fast.
Meghan Bobrowsky
@MeghanBobrowsky
Oct 11, 2025
Saturday scoop: Thinking Machines Lab co-founder Andrew Tulloch has joined Meta, the startup confirmed. W/ @keachhagey
87K
rohan anil
@_arohan_
Oct 9, 2024
I got to coauthor papers with two Nobel prize winners, one in Physics and one in Chemistry 😁
27K
rohan anil
@_arohan_
Dec 6, 2023
It’s been a privilege to work alongside with our gemini leads and team (across Google DeepMind, Research and Alphabet) in one of the most interesting and challenging projects of my career. We have three versions of Gemini: (a) Ultra (b) Pro and (c) Nano We make significant
Jeff Dean
@JeffDean
Dec 6, 2023
I’m very excited to share our work on Gemini today! Gemini is a family of multimodal models that demonstrate really strong capabilities across the image, audio, video, and text domains. Our most-capable model, Gemini Ultra, advances the state of the art in 30 of 32 benchmarks,
157K
rohan anil
@_arohan_
Jun 22, 2022
A new image generation model just dropped. parti.research.google Great work by the team! + Auto-regressive, encoder->decoder Transformer + Classifier-free sampling. + ViT-VQGAN Really amazing results: Image from the website.