TheGradient Profile Banner
Hossein Mobahi Profile
Hossein Mobahi

@TheGradient

Followers
6K
Following
5K
Media
120
Statuses
1K

Senior Research Scientist @GoogleDeepMind. I ∈ Optimization ∩ Machine Learning. Fan of @IronMaiden🤘.Here to discuss research 🤓

Mountain View, CA
Joined December 2010
Don't wanna be here? Send us removal request.
@TheGradient
Hossein Mobahi
1 month
RT @bremen79: As promised, we put on Arxiv the proof we did with Gemini. This shows that the Polyak stepsize not o….
0
62
0
@TheGradient
Hossein Mobahi
3 months
RT @FeiziSoheil: 🚀 Introducing Data Agents— generate accurate, reasoning-based AI benchmarks from your own data in minutes!. ⚡ With Data Ag….
0
31
0
@TheGradient
Hossein Mobahi
3 months
It is time! Applications for the global @Google PhD Fellowship Program are NOW open.
@TheGradient
Hossein Mobahi
4 months
Applications for the global @Google PhD Fellowship Program opens on Apr 10th. Fellowships support graduate students doing exceptional and innovative research in computer science and related fields as they pursue their PhD. Learn more and apply by May 15 at
1
4
56
@TheGradient
Hossein Mobahi
4 months
Applications for the global @Google PhD Fellowship Program opens on Apr 10th. Fellowships support graduate students doing exceptional and innovative research in computer science and related fields as they pursue their PhD. Learn more and apply by May 15 at
1
41
218
@TheGradient
Hossein Mobahi
5 months
(2/2) Not at UCLA but interested in this work? Check Thanks to our fantastic intern @unregularized (soon to return full-time!) for leading this project, along with collaborators @ynd and Atish. Thanks to my UCLA host @baharanm for the seminar invitation!.
2
1
20
@TheGradient
Hossein Mobahi
5 months
(1/2) Ever wondered why Sharpness-Aware Minimization (SAM) yields greater generalization gains in vision than in NLP? I'll discuss this at @UCLA CS-201 seminar February 18th, relating it to the balance of SAM's impact on logit statistics vs model geometry.
1
10
59
@TheGradient
Hossein Mobahi
6 months
RT @_tim_brooks: DeepMind has ambitious plans to make massive generative models that simulate the world. I'm hiring for a new team with thi….
0
223
0
@TheGradient
Hossein Mobahi
6 months
RT @SuryaGanguli: Our new paper! "Analytic theory of creativity in convolutional diffusion models" lead expertly by @MasonKamb https://t.co….
0
72
0
@TheGradient
Hossein Mobahi
7 months
Having read Francis's popular/insightful blog posts, I appreciate his ability to explore seemingly familiar topics and reveal their hidden depths. His clear/accessible presentation makes me believe this will be one of the best resources of our time for learning foundational ML.
@BachFrancis
Francis Bach
7 months
My book is (at last) out, just in time for Christmas!.A blog post to celebrate and present it:
Tweet media one
0
0
18
@TheGradient
Hossein Mobahi
7 months
2/2. Algorithms & optimization.Fundamentals & Applied Science.Health research.HCI.Machine learning & data mining.Machine perception.Natural language processing.Networking.Privacy, Safety, and Security.Quantum computing.Software engineering & programming languages.Systems.
0
0
3
@TheGradient
Hossein Mobahi
7 months
1/2 Just a reminder about Google Research Scholar Program, providing up to $60K unrestricted gifts to recognize early-career professors and support world-class research at institutions around the world. This year, we are particularly interested in the following research areas. .
@TheGradient
Hossein Mobahi
7 months
Applications are open for the @GoogleAI's Research Scholar Program, a program that supports early-career professors conducting research in fields relevant to Google. Learn more and apply by January 27 at
1
3
12
@TheGradient
Hossein Mobahi
7 months
Applications are open for the @GoogleAI's Research Scholar Program, a program that supports early-career professors conducting research in fields relevant to Google. Learn more and apply by January 27 at
0
2
22
@TheGradient
Hossein Mobahi
8 months
RT @QuanquanGu: Today’s the day to launch! Introducing MARS (Make vAriance Reduction Shine): the ultimate LLM optimizer. Let’s unite, innov….
0
39
0
@TheGradient
Hossein Mobahi
8 months
RT @maksym_andr: 🚨I'm on the faculty job market this year!🚨. My research focuses on AI safety & generalization. I'm interested in developin….
0
44
0
@TheGradient
Hossein Mobahi
8 months
Workshop on Theory & Practice of Foundation Models (organized by @mirrokni and myself) will happen this week @GoogleAI Mountain View. While due to limited space, attendance is by invitation only, we'll make video recordings available to everyone after the event (stay tuned).
3
23
135
@TheGradient
Hossein Mobahi
8 months
RT @jacobandreas: Interested in a postdoc at MIT? Apply for the METEOR fellowship, which aims to support exceptional researchers in compute….
0
25
0
@TheGradient
Hossein Mobahi
8 months
Unique opportunity to work with a world-class LLM researcher.
@hamidpalangi
Hamid Palangi
8 months
I am seeking student researchers to hire for 2025 focusing on Multi-Agent LLMs and Inference Time Decoding Algorithms. Ideal candidates are last year PhD students with relevant publications. If interested, please email your CV to hamidpalangi@google.com. Thank you!.
1
1
26
@TheGradient
Hossein Mobahi
8 months
RT @FeiziSoheil: 🚀 Exciting news! We’re launching RELAI with a mission to make AI reliability accessible and achievable for everyone. Our….
0
40
0
@TheGradient
Hossein Mobahi
9 months
These barriers repel gradient descent and prevent it from converging to their enclosed minima. This allows gradient descent to find flatter minima, even when initialized near a sharper one (same earlier initialization).
0
0
0