Picture

Gaurav Menghani @GauravML

Senior Staff Software Engineer @ Google Research. Author of the Efficient Deep Learning book. Opinions are my own, obviously. Memento mori. gaurav.ai Bay Area, California. Joined June 2019
  • Tweets
    575
  • Followers
    880
  • Following
    818
  • Likes
    7K
GauravML Profile Picture

Gaurav Menghani @GauravML

4 weeks ago

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/

GauravML Profile Picture

Gaurav Menghani @GauravML

a month ago

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 retweeted
zackkanter Profile Picture

Zack Kanter @zackkanter

a month ago

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

linamkhan Profile Picture

Lina Khan @linamkhan

a month ago

Lina Khan deciding if you should be permitted to sell your startup or be forced to deliver additional shareholder value. https://t.co/vHpX10eo5r

Gaurav Menghani retweeted
williamallen Profile Picture

William Allen @williamallen

2 months ago

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 retweeted
osanseviero Profile Picture

Omar Sanseviero @osanseviero

2 months ago

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…

GauravML Profile Picture

Gaurav Menghani @GauravML

2 months ago

Proud to have contributed to Gemma3N via LAuReL (arxiv.org/abs/2411.07501). developers.googleblog.com/en/introducing…

GauravML Profile Picture

Gaurav Menghani @GauravML

3 months ago

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

GauravML Profile Picture

Gaurav Menghani @GauravML

3 months ago

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

GauravML Profile Picture

Gaurav Menghani @GauravML

4 months ago

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)

googleaidevs Profile Picture

Google AI Developers @googleaidevs

4 months ago

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)

Gaurav Menghani retweeted
JeffDean Profile Picture

Jeff Dean @JeffDean

5 months ago

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!

joshwoodward Profile Picture

Josh Woodward @joshwoodward

5 months ago

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!

Gaurav Menghani retweeted
JeffDean Profile Picture

Jeff Dean @JeffDean

7 months ago

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…

dwarkesh_sp Profile Picture

Dwarkesh Patel @dwarkesh_sp

7 months ago

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… https://t.co/Qve6ZOdpKD

GauravML Profile Picture

Gaurav Menghani @GauravML

7 months ago

Precisely. Ask India the value of good neighbors. Canada is probably the best neighbor any country could ask for.

paulg Profile Picture

Paul Graham @paulg

7 months ago

Precisely. Ask India the value of good neighbors. Canada is probably the best neighbor any country could ask for.

GauravML Profile Picture

Gaurav Menghani @GauravML

9 months ago

Gemini 2.0 Flash is a huge leap in terms of ML efficiency techniques that have gone in to get this model to beat a significantly bigger model. Just makes you sit back and marvel.

JeffDean Profile Picture

Jeff Dean @JeffDean

9 months ago

Gemini 2.0 Flash is a huge leap in terms of ML efficiency techniques that have gone in to get this model to beat a significantly bigger model. Just makes you sit back and marvel.

Trends for United States

#UFCParis
52,3 B posts
Baylor
12,5 B posts
Ruffy
25 B posts
Staub
2.731 posts
Iowa
34,1 B posts
Julian Sayin
2.518 posts
Paul Craig
2.834 posts
Karen
264 B posts
Stoops
1.926 posts
Kentucky
12 B posts
Austin Simmons
Ole Miss
5.520 posts
Oregon
36,1 B posts
Gundy
1.658 posts
Salter
1.408 posts
Calzada
2.260 posts
Oklahoma State
4.768 posts
Grambling
3.942 posts
Dante Moore
Austin Peay
1.986 posts

You might like

LLM Efficiency PhD @ Edinburgh | 🥇🥈 @ Flunkyball Polish Championships | 🥇 @ Jerry Hunter Pub's Bowling Tournament | 50000 🏆 & Legendary II @ Brawl Stars
Piotr Nawrot
@p_nawrot
8K Followers
Research Scientist @DeepMind working on Gemini Thinking
Aditi Mavalankar
@aditimavalankar
2K Followers
Chief AI Scientist @databricks via MosaicML.
Jonathan Frankle
@jefrankle
20K Followers
Researcher @bfl_ml 🌲, incoming Assistant Professor @TelAvivUni (2026). Former @GoogleDeepMind, @AIatMeta. Exploring and exploiting deep neural networks 🕵🏻‍♀️
Hila Chefer
@hila_chefer
4K Followers
Reinforcement Learner, Adjunct Prof at McGill. Ex MSL Meta, DeepMind, Brain, Mila, IIT Bombay. NeurIPS Best Paper
Rishabh Agarwal
@agarwl_
17K Followers
/google_deepmind/gemini/.
Mostafa Dehghani
@m__dehghani
10K Followers
Researcher @AnthropicAI Prev:🦙 @aiatmeta, @allen_ai PhD @uwcse + @uwnlp
Sachin Gururangan
@ssgrn
6K Followers
Figuring out AI @allen_ai, open models, RLHF, fine-tuning, etc Contact via email. Writes @interconnectsai Wrote The RLHF Book Mountain runner
Nathan Lambert
@natolambert
56K Followers
ML Engineer @ML6team, part-time at @huggingface. @KU_Leuven grad. General interest in machine learning, deep learning. Making AI more accessible for everyone!
Niels Rogge
@NielsRogge
16K Followers
Senior Director, Applied Science @Oracle | Past - Manager + Principal Scientist @IBMResearch AI | Tweets are my own opinion
Avi Sil
@aviaviavi__
2K Followers
Faculty at the Indian Institute of Science, Bangalore. PhD from @LTIatCMU.
Danish Pruthi
@danish037
11K Followers
Head of Responsible AI, CTO office, @Bloomberg. (he/him) Formerly LLMs @ Google Brain / Harvard. views my own
Sebastian Gehrmann
@sebgehr
6K Followers
Professor of Computer Science at @UniTrento. Head of Research Unit at @FBK_research. Interests in Computer Vision, Deep Learning and Robotics
Elisa Ricci
@eliricci_
1K Followers
Learning machine learning at Google DeepMind.
Prateek Jain
@jainprateek_
7K Followers
Dr. Manish Gupta is Director, Google DeepMind, based in Bangalore.
Manish Gupta
@ManishGuptaMG1
6K Followers