GauravML's profile picture. Senior Staff Software Engineer @ Google Research. Author of the Efficient Deep Learning book. Opinions are my own, obviously. Memento mori.

Gaurav Menghani

@GauravML

Senior Staff Software Engineer @ Google Research. Author of the Efficient Deep Learning book. Opinions are my own, obviously. Memento mori.

Pinned

Excited to share a survey of the vast landscape of efficiency in deep learning on how to make your deep learning models smaller, faster, and better! arxiv.org/abs/2106.08962 (1/n)


One of the nicest people in the Chess community, gone too soon.

The Naroditsky family shares the sad news of Daniel’s unexpected passing. Daniel was a talented chess player, educator, and beloved member of the chess community. We ask for privacy as the family grieves.

CLTchesscenter's tweet image. The Naroditsky family shares the sad news of Daniel’s unexpected passing. Daniel was a talented chess player, educator, and beloved member of the chess community. We ask for privacy as the family grieves.
CLTchesscenter's tweet image. The Naroditsky family shares the sad news of Daniel’s unexpected passing. Daniel was a talented chess player, educator, and beloved member of the chess community. We ask for privacy as the family grieves.


Gaurav Menghani reposted

A fun conversation with the amazing @shripati and his team at @Primevp_in! Thanks a lot for hosting me.

What happens when one of @GoogleDeepMind's top scientists sits down to unpack AI’s past, present & future? The full episode with @jainprateek_ is here. 🎙 Topics you can’t miss: 🔹 Deep learning → transformers → generative AI 🔹 India’s once-in-a-generation chance to lead in…

Primevp_in's tweet card. Why India Must Lead in Deep AI Research | Insights from Google...

youtube.com

YouTube

Why India Must Lead in Deep AI Research | Insights from Google...



New post on 'Noam Notation' or Shape Suffixes. Just a quick way to make modeling code slightly more readable. Give it a read, and leave a comment if I missed something / got something wrong. blog.gaurav.ai/noam-notation/


Doing something new: I will be writing about algorithmic efficiency techniques every other week or so. Starting off with the the dynamic duo of KV Caching and KV Sharing. Feel free to give it a read, and drop a comment if I missed something. blog.gaurav.ai/2025/08/05/kv-…


Gaurav Menghani reposted

Lina Khan deciding if you should be permitted to sell your startup or be forced to deliver additional shareholder value.

zackkanter's tweet image. Lina Khan deciding if you should be permitted to sell your startup or be forced to deliver additional shareholder value.

A great reminder that letting startups grow into independently successful businesses, rather than be bought up by existing giants, can generate enormous value. A win for employees, investors, innovation, and the public.



Gaurav Menghani reposted

I don’t think he’s ever told the story, but it’s worth telling. When we were selling @Behance to Adobe many years ago, @scottbelsky made a spreadsheet of every employee (32 of us at the time) and personally negotiated each persons title, salary and incentive structure, and made…


Gaurav Menghani reposted

Want to learn about the research behind Gemma 3n? Altup - arxiv.org/abs/2301.13310 LAuReL - arxiv.org/abs/2411.07501 MatFormer - arxiv.org/abs/2310.07707 Activation sparsity - arxiv.org/abs/2506.06644 Universal Speech Model - arxiv.org/abs/2303.01037 Blog - developers.googleblog.com/en/introducing…


The dopamine rush of getting some hard ML projects done is something else.


Yet another AI Overview win. None of the individual pages could have given me this answer.

GauravML's tweet image. Yet another AI Overview win. 

None of the individual pages could have given me this answer.

So glad to see this released! Amazing work from a super-talented team :) LAuReL is also a part of the model efficiency goodness that has gone into making this model a reality. (arxiv.org/abs/2411.07501)

✨ Introducing Gemma 3n, available in early preview today. The model uses a cutting-edge architecture optimized for mobile on-device usage. It brings multimodality, super fast inference, and more.



Gaurav Menghani reposted

College students, you can now get all kinds of nice things for free! Try out Gemini Advanced, NotebookLM Plus, some exciting disk space, and more!

This school year AND next school year -> Free! This comes with Gemini Advanced and: * NotebookLM Plus * Gemini in Google Docs, Sheets and Slides * Whisk * 2TB of storage



Gaurav Menghani reposted

I'm delighted to have joined my good friend and colleague @NoamShazeer for a 2+hour conversation with @dwarkesh_sp about a wide range of topics (early Google, ML hardware, training trillion token LLMs in 2007, model sparsity, continual learning, and more). Thanks for a fantastic…

JeffDean's tweet image. I'm delighted to have joined my good friend and colleague @NoamShazeer for a 2+hour conversation with @dwarkesh_sp about a wide range of topics (early Google, ML hardware, training trillion token LLMs in 2007, model sparsity, continual learning, and more).

Thanks for a fantastic…

The @JeffDean & @NoamShazeer episode. We talk about 25 years at Google, from PageRank to MapReduce to the Transformer to MoEs to AlphaChip – and soon to ASI. My favorite part was Jeff's vision for AGI as one giant MoE that is grown in bits and pieces over time like a forest,…



Loading...

Something went wrong.


Something went wrong.