Alireza Fathi @alirezafathi Twitter profile

Last Seen Profiles

@wcsSMS

@osushivip

@Vk1262064123262

@tanlinepeach

@PasutriAsli2

@absoghar93

@CoachSmithMCHS

@9nH4dz5baKK1gZU

@aoo1183

@TLsabellah

@DavidMDrever

@ITFFOCAustralia

@bokeplokalmalam

@Luck0069

@zayndailynews

@Aalbaagarciaa

@joao626303

@shen_ze21528

@Rainlily56

@matsuba1

@nagimarzouk

@Saintamoure

@8k_slim

@LAPDWestLA

@stwmaniax

@Hensch10

@Km9_2_

@hero198x

@estofaditos

@Isluobei

@gelu78

@mika_sec

@adelacreations

@stwmaniax

@nnnxxx456

@penyukastw21

Alireza Fathi

@alirezafathi

17 days

Our team at Google DeepMind is seeking a Research Scientist with a strong publication record (multiple first-author papers) on multi-modal LLMs in top ML venues like NeurIPS, ICLR, CVPR. Email me at af_hiring @google .com @CordeliaSchmid

4

47

377

Alireza Fathi

@alirezafathi

4 years

Robotics at Google has released a very high quality dataset of scanned objects. It could enable interesting research in 3d shape modeling.

2

90

311

Alireza Fathi

@alirezafathi

3 years

Jitendra Malik's thoughts on Foundation Models, in the Stanford HAI workshop

Workshop on Foundation Models: Day 1

The Center for Research on Foundation Models (CRFM), a new initiative of the Stanford Institute for Human-Centered Artificial Intelligence (HAI), hosted the ...

www.youtube.com

5

40

185

Alireza Fathi

@alirezafathi

4 years

We have released TensorFlow 3D!

Google AI

@GoogleAI

4 years

Announcing the release of TensorFlow 3D, a set of training and evaluation pipelines for state-of-the-art 3D semantic segmentation, object detection and instance segmentation, with support for distributed training. Check it out and download the code at

10

336

1K

2

19

79

Alireza Fathi

@alirezafathi

2 years

Augmenting Large Language & Visual models with Retrieval helps the model to answer questions that were not present in the training data. REVEAL is one of the recent works by our team @acbuller , @ahmetius , @jesu9 , @MrZiruiWang , David Ross, @CordeliaSchmid

REVEAL: Retrieval-Augmented Visual-Language Pre-Training with...

In this paper, we propose an end-to-end Retrieval-Augmented Visual Language Model (REVEAL) that learns to encode world knowledge into a large-scale memory, and to retrieve from it to answer...

arxiv.org

0

6

37

Alireza Fathi

@alirezafathi

4 years

Most of the previous work on 3d object detection use only one frame of data. In our #eccv2020 paper, we present a 3d sparse LSTM model that achieves more accurate results when applied to a sequence of point clouds.

0

5

29

Alireza Fathi

@alirezafathi

4 years

Our recent work on object-centric neural rendering. Our new formulation makes it possible to move the objects around in the scene and still be able to render high quality images from different views.

Michelle Guo

@mshlguo

4 years

We made NeRF compositional! By learning object-centric neural scattering functions (OSFs), we can now compose dynamic scenes from captured images of objects. Website: Joint work with @alirezafathi @jiajunwu_cs Thomas Funkhouser

4

44

254

1

2

30

Alireza Fathi

@alirezafathi

5 years

I am glad that our #cvpr2020 reviews are very positive, but at the same time I am very worried that the quality of the reviews have significantly degraded compared to few years ago.

1

0

26

Alireza Fathi

@alirezafathi

4 years

Congratulations to Yue Wang (research intern), Rui Huang (AI resident), Wanyue Zhang (AI resident) and @_abhijit_kundu_ for getting their papers accepted to #eccv2020 .

1

0

24

Alireza Fathi

@alirezafathi

1 year

Today marks my 7th year at Google! How time flies! Thank you, Google, for giving me the opportunity to work on what I enjoy...

4

0

20

Alireza Fathi

@alirezafathi

1 year

Here is our Google AI blog post on AVIS, a Large Language Model Agent that achieves state-of-the-art results on visual information seeking tasks. @acbuller @ahmetius @jesu9 @CordeliaSchmid

Google AI

@GoogleAI

1 year

Today on the blog, read all about AVIS — Autonomous Visual Information Seeking with Large Language Models — a novel method that iteratively employs a planner and reasoner to achieve state-of-the-art results on visual information seeking tasks →

36

212

812

0

4

18

Alireza Fathi

@alirezafathi

4 years

Our ECCV paper on "Pillar-based Object Detection for Autonomous Driving" that achieves state of the art results on 3d object detection on the Waymo Open Dataset.

0

2

17

Alireza Fathi

@alirezafathi

1 year

REVEAL will be a highlight at @CVPR . Looking forward to discussing it in more details there with @acbuller , @ahmetius , @jesu9 , @CordeliaSchmid

Google AI

@GoogleAI

1 year

Learn how REVEAL, an end-to-end retrieval-augmented visual-language model that learns to use multi-source multi-modal data to answer knowledge-intensive queries, achieves state-of-the-art results on visual question answering and image caption tasks.

16

90

280

2

17

Alireza Fathi

@alirezafathi

5 years

Another CVPR2020 paper by our group on detecting 3d objects and predicting their 3d shapes

0

13

Alireza Fathi

@alirezafathi

3 years

We are gonna be able to go back to office starting July 12th! Never thought I would be this excited to go back to work in person :)

1

0

12

Alireza Fathi

@alirezafathi

4 years

Having to take shelter in place, I have been spending some time on gardening! Here is how our sour cherry tree is looking like today!

0

12

Alireza Fathi

@alirezafathi

6 years

Neural Networks seem to follow a puzzlingly simple strategy to classify images

0

2

12

Alireza Fathi

@alirezafathi

4 years

Looking forward to presenting our work on 3d scene understanding in the Deep Learning 2.0 Virtual Summit.

Hollie Jaques

@reworkhollie

4 years

I am looking forward to Alireza Fathi presenting his research advancements at the Deep Learning 2.0 Virtual Summit, Jan 2021. Alireza is currently working on object detection and segmentation in 3D. Join us, and Alireza in January: #computervision

0

2

0

1

12

Alireza Fathi

@alirezafathi

4 years

One of the sad things during this pandemic is to observe the ugly gap between the rich and the poor. At the same time that the rich stays home and orders groceries online to avoid exposure, the poor shops those groceries in store and delivers them to make a living

0

1

11

Alireza Fathi

@alirezafathi

1 year

🚀Introducing AVIS: a groundbreaking system that couples #LLM powered planning & reasoning with external tools, resulting in #StateOfTheArt performance on VQA datasets that demand external knowledge! 🧠🔍

AK

@_akhaliq

1 year

AVIS: Autonomous Visual Information Seeking with Large Language Models paper page: In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically

2

26

86

0

4

11

Alireza Fathi

@alirezafathi

5 years

Vote for CVPR 2023 at Vancouver if you are at #CVPR2019

Greg Mori

@greg_mori

5 years

It’s hard to think of a better place than #Vancouver for #CVPR 2023. Beyond our strong team, it’s fitting that a conference on vision should take place in one of the most beautiful spots on earth. Check out our awesome bid #AINorth #AI #computervision

0

29

84

0

3

11

Alireza Fathi

@alirezafathi

2 years

I am sorry to see colleagues and friends getting affected by mass layoffs in recent days. Please reach out and I would try my best to help with any resources I can think of. Hopefully things will bounce back soon.

0

11

Alireza Fathi

@alirezafathi

5 years

Great work Francis Engelman! Our CVPR 2020 paper achieving the state of the art results on 3d instance segmentation in ScanNet and S3DIS :)

Matthias Niessner

@MattNiessner

5 years

"3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation" #CVPR2020 We perform SemInstSeg by proposal aggregation using a GraphConvNet to model higher-order proposal interactions! Great results on ScanNet and S3DIS :) @FrancisEngelman

0

15

59

1

0

11

Alireza Fathi

@alirezafathi

7 months

Check out our CVPR paper on generative retrieval for web-scale entity recognition!

Mathilde Caron

@mcaron31

7 months

Happy to introduce GERALD - our new VLM that recognizes 6M+ entities, an exciting step towards Web-scale visual entity recognition! Predictions are simply made by auto-regressively decoding a code representing the entity name. Check out our CVPR24 paper:

2

19

131

4

0

9

Alireza Fathi

@alirezafathi

7 years

We have just released the instance segmentation support for the Tensor Flow Object Detection API. #TensorFlow #ObjectDetection #Google #API #Segmentation #InstanceSegmentation

0

5

9

Alireza Fathi

@alirezafathi

6 years

0

2

9

Alireza Fathi

@alirezafathi

4 years

Something interesting that I just learned today! Are green, red, yellow and orange bell peppers different or the same?

0

8

Alireza Fathi

@alirezafathi

5 years

Sundar Pichai is now the CEO of Alphabet...

1

0

8

Alireza Fathi

@alirezafathi

5 years

Great job Steven. A network for predicting surface normals running in real-time on a pixel 2 phone @StevenDHickson @aCromulentName Kevin Murphy @irrfaan

0

1

8

Alireza Fathi

@alirezafathi

4 years

Google has launched it's best thing for everything guide. No need for consumer reports subscription anymore!

0

1

8

Alireza Fathi

@alirezafathi

1 year

In this work led by @ahmetius we show that image recognition can benefit when retrieving similar images from a web-scale corpus of image-text pairs.

Ahmet Iscen

@ahmetius

1 year

New #CVPR2023 paper "Improving Image Recognition by Retrieving from Web-Scale Image-Text Data". We improve the recognition capabilities of the model by retrieving images/texts from large-scale memory. Joint work with @alirezafathi and @CordeliaSchmid .

1

9

79

0

7

Alireza Fathi

@alirezafathi

4 years

Here is the link if you are interested in applying for the Google Summer Research Internship :)

0

7

Alireza Fathi

@alirezafathi

6 years

After almost a decade and billions in outside investment, Magic Leap's first product is finally on sale for $2,295. Here's what it's like. #MagicLeap

0

1

6

Alireza Fathi

@alirezafathi

5 years

Great course for learning deep reinforcement learning!

Sergey Levine

@svlevine

5 years

Want to learn deep RL? My deep RL course now has a permanent course number (CS285) and is being offered this semester: Lecture videos here (so far, we've gotten through most of model-free RL, model-based RL coming up next):

14

476

2K

0

1

6

Alireza Fathi

@alirezafathi

5 years

Waymo Truck

1

7

Alireza Fathi

@alirezafathi

4 years

An interesting blog post on using unity for creating synthetic data for object detection and beyond

0

2

7

Alireza Fathi

@alirezafathi

5 years

Moore's law vs. reality animation. Very cool.

Lionel Page

@page_eco

5 years

Fascinating: Moore’s Law predictions vs actual growth in transistor count. by @datagrapha

58

3K

5K

0

1

5

Alireza Fathi

@alirezafathi

5 years

This would be a great resource for software engineers and researchers outside Google

Peyman Milanfar

@docmilanfar

5 years

Google's software engineering best practices facilitate consistency & productivity. All code is peer reviewed for clarity, correctness, and adherence to standards. We've just published these practices. Highly recommended for any lab, academic or otherwise.

0

21

57

0

6

Alireza Fathi

@alirezafathi

1 year

These short Neurips reviews could be done by LLMs! Probably we don't need reviewers anymore...LLM would write the review and AC makes the decision by looking at the review and the paper!

2

1

6

Alireza Fathi

@alirezafathi

4 years

I have a #TensorFlow joke but I need to be in eager mode!

0

1

6

Alireza Fathi

@alirezafathi

3 years

OpenAI's new model fine-tuned from GPT3 for summarizing books!

1

6

Alireza Fathi

@alirezafathi

1 year

Happy 25th birthday Google 🎉

Jeff Dean (@🏡)

@JeffDean

1 year

Happy 25th Birthday Google! 🎉 I have gotten incredible enjoyement from being along for the ride for 24+ of these years. When I joined, we were a handful of people wedged into a small office area in downtown Palo Alto above what is now a T-Mobile store. 1/

54

218

2K

1

0

6

Alireza Fathi

@alirezafathi

5 years

Congrats to Martial Hebert for becoming the new dean of School of Computer Science at CMU

Hebert Named Dean of Carnegie Mellon’s Top-Ranked School of Computer Science - Robotics Institute...

Acclaimed computer scientist and AI researcher has led Robotics Institute since 2014 PITTSBURGH—Martial Hebert, a leading researcher in computer vision and robotics, has been named dean of Carnegie...

www.ri.cmu.edu

0

2

5

Alireza Fathi

@alirezafathi

6 years

0

5

Alireza Fathi

@alirezafathi

5 years

An interesting blog post on transformers in deep learning models

Peter Bloem (@[email protected])

@pbloemesquire

5 years

New blogpost! Transformers from scratch. Modern transformers are super simple, so we can explain them in a really straightforward manner. Includes pytorch code.

17

453

2K

0

5

Alireza Fathi

@alirezafathi

4 years

An interesting podcast with Jitendra Malik on challenges in computer vision

1

0

5

Alireza Fathi

@alirezafathi

5 years

@elonmusk One keeps a car for 5 years on average. I promise u there won't be self driving cars in streets five years from now :)

1

0

5

Alireza Fathi

@alirezafathi

3 years

@fdellaert So you submitted HiNeRF to CVPR? :D

0

5

Alireza Fathi

@alirezafathi

6 years

@realDonaldTrump Remove travel ban! #RemoveTravelBan

0

3

Alireza Fathi

@alirezafathi

5 years

'3D' is the most frequently used keyword after 'detection' in CVPR 2019

0

1

5

Alireza Fathi

@alirezafathi

5 years

Interesting to know! Number of deaths by risk factor

0

1

3

Alireza Fathi

@alirezafathi

4 years

@JeffDean @MelMel1082 Maximum possible distance on earth is about 19,000km. So this one is probably very unlikely to beat :)

Extremes on Earth - Wikipedia

en.m.wikipedia.org

0

4

Alireza Fathi

@alirezafathi

1 year

@docmilanfar That probably is right. But raising $90M in the current environment where most startups are having a hard time raising any money is a very strong signal

2

0

4

Alireza Fathi

@alirezafathi

4 years

@mattytgray @GoogleAI 3D object detection and segmentation for self driving cars / robotics, augmented reality, etc.

0

4

Alireza Fathi

@alirezafathi

1 year

@_akhaliq Everything is now "Everything Everywhere All at Once"!

0

4

Alireza Fathi

@alirezafathi

1 year

@negar_rz @3scorciav @CVPR @ICCVConference I was thinking LLM mostly does a summarization and comparison to previous work. Not necessarily scoring the paper. This would make ACs job much easier, but AC would make the final decision by both looking at the summary and the paper itself.

1

0

2

Alireza Fathi

@alirezafathi

4 years

I don't play video games, but if I do, I play FIFA! And it will be great if I have a work related reason to play!

'FIFA 21' comes to Google Stadia on March 17th

EA is bringing more than one football game to Stadia. Today, the publisher announced that FIFA 21, the latest entry in ‘the beautiful game’ franchise, will available to stream from March 17th. It...

www.engadget.com

0

4

Alireza Fathi

@alirezafathi

4 years

This is how betting odds changed after last night's debate

0

4

Alireza Fathi

@alirezafathi

9 months

Spread between 2-year and 30-year U.S. Treasury securities over time!

0

1

4

Alireza Fathi

@alirezafathi

6 years

GPipe, an Open Source Library for Efficiently Training Large-scale Neural Network Models

0

4

Alireza Fathi

@alirezafathi

5 years

Pretty exciting project at Google X

0

4

Alireza Fathi

@alirezafathi

1 year

"Model the world, not the data"!

1

0

4

Alireza Fathi

@alirezafathi

4 years

Folks in our team have released the Tensorflow 2.0 version of Object Detection API #tensorflow #ObjectDetection

1

2

4

Alireza Fathi

@alirezafathi

6 years

Google's plan to build 6,600 houses in Mountain View

0

4

Alireza Fathi

@alirezafathi

5 years

This might be a useful idea for last minute researchers like myself :)

Devi Parikh

@deviparikh

5 years

I have a system to plan writing papers for conference deadlines. My students and some collaborators know about it. With the ICLR 2020 deadline coming up, I thought this might be a good time to share this with a wider audience.

10

230

928

0

3

Alireza Fathi

@alirezafathi

5 years

Ego is the anesthesia that deadens the pain of stupidity #famousquotes

0

2

Alireza Fathi

@alirezafathi

5 years

It is true 🙂

Brent Mittelstadt

@b_mittelstadt

5 years

This might be the perfect overhyped #AI meme. Courtesy of @c_russl

12

709

2K

0

3

Alireza Fathi

@alirezafathi

6 years

I feel so out of touch with the people and what they care about around me. I thought I will look at Google trends to see what people are thinking about politics or economic situation, but I realized the main thing they care about at this moment is #NFL

0

3

Alireza Fathi

@alirezafathi

6 years

Fill in the blanks! What is your prediction on where this curve is going? #NASDAQ

0

3

Alireza Fathi

@alirezafathi

5 years

@drfeifei @yukez @leto__jean @EmmaBrunskill @silviocinguetta Congratulations @yukez and @drfeifei . Have been lucky to work with both of you

0

3

Alireza Fathi

@alirezafathi

6 years

Wow...Go Man U...What a come back...

0

3

Alireza Fathi

@alirezafathi

5 years

Rumors that apparently Apple is buying drive ai

0

3

Alireza Fathi

@alirezafathi

5 years

More than 17 million Americans have more than 1 million dollars in assets!

0

3

Alireza Fathi

@alirezafathi

5 years

Amazing photos from Pixel 4 show how computer vision and machine learning can give a strong boost to the camera hardware

0

3

Alireza Fathi

@alirezafathi

1 year

200 Billion galaxies in the observable universe, and each galaxy has on average 100 Million stars! Don't take your life so serious stressing out for things that do not even matter on multi-galaxy level!

0

3

Alireza Fathi

@alirezafathi

5 years

Google just publicly released its DeepFakes dataset so all researchers can work on it.

Sundar Pichai

@sundarpichai

5 years

Detecting deepfakes is one of the most important challenges ahead of us. Following our release of a synthetic audio dataset in Jan, we're releasing a large dataset of visual deepfakes to support researchers working on synthetic video detection #GoogleAI

75

517

3K

0

3

Alireza Fathi

@alirezafathi

4 years

0

3

Alireza Fathi

@alirezafathi

6 years

Working from Google SF today! Look at the view... #sf #working #Google #googlesf

0

3

Alireza Fathi

@alirezafathi

5 years

Waymo open dataset is publicly released. Orders of magnitude larger than Kitti

Waymo

@Waymo

5 years

Today, we're launching our Waymo Open Dataset. This high resolution lidar and camera data has been collected by our self-driving cars across a diverse range of situations. We're excited to share it directly with the research community. Download now:

18

338

900

0

3

Alireza Fathi

@alirezafathi

5 years

NeurIPS2019 Competition tracks are released, including a 20K competition on 3d object detection organized by Lyft #NeurIPS #NeurIPS2019

0

3

Alireza Fathi

@alirezafathi

4 years

Three industries that could be transformed by computer vision: Farming, Healthcare, Retail

0

2

Alireza Fathi

@alirezafathi

5 years

A nice literature review on deep graph networks

GitHub - DeepGraphLearning/LiteratureDL4Graph: A comprehensive collection of recent papers on graph...

A comprehensive collection of recent papers on graph deep learning - DeepGraphLearning/LiteratureDL4Graph

github.com

0

2

Alireza Fathi

@alirezafathi

4 years

@docmilanfar Why would someone talk about their rejected papers :) the motivation behind advertising the accepted papers is that others read them and cite them...

1

0

2

Alireza Fathi

@alirezafathi

5 years

I went to my first CVPR in 2008 which was an order of magnitude smaller than this year's conference... #cvpr #cvpr19

IEEE ComputerSociety

@ComputerSociety

5 years

How the @cvpr2019 Conference -- tech's premier event for computer vision -- broke records on all fronts. Cite self-driving cars & your social media apps, among other factors, says @wjscheirer of @NotreDame . #ieeecs #cvpr #cvpr19 #cvpr2019 #selfdrivingcars

0

3

5

1

0

2

Alireza Fathi

@alirezafathi

1 year

@sirbayes

REVEAL: Retrieval-Augmented Visual-Language Pre-Training with...

In this paper, we propose an end-to-end Retrieval-Augmented Visual Language Model (REVEAL) that learns to encode world knowledge into a large-scale memory, and to retrieve from it to answer...

arxiv.org

0

2

Alireza Fathi

@alirezafathi

5 years

On Netflix beginning Sep 20

0

2

Alireza Fathi

@alirezafathi

5 years

This is how much an average U.S. worker has saved in their 401(k)

0

2

Alireza Fathi

@alirezafathi

6 years

0

1

Alireza Fathi

@alirezafathi

1 year

@kohjingyu Their numbers are significantly below current state of the art so not sure :)

0

2

Alireza Fathi

@alirezafathi

6 years

Wow! Apple is only $15B away from being a trillion dollar company. #Apple #stocks

0

2

Alireza Fathi

@alirezafathi

4 years

Oh i have been wanting this so bad

0

2

Alireza Fathi

@alirezafathi

6 years

@realDonaldTrump I support stopping illegal immigration! You should remove travel ban which stops legal immigration ASAP though!

0

1

2

Alireza Fathi

@alirezafathi

4 years

This whole last few months feels like a dream. One weird part of this dream is that everyday I wake up I see stocks going up! #ShelterInPlace

0

2

Alireza Fathi

@alirezafathi

1 year

Apparently based on statistics, Twitter is tilted towards young males with a college education, while Instagram is focused on female users in the 18 to 49 crowd, with a higher portion of people without a High School education. So makes sense for Meta to go after this market. What

0

2

Alireza Fathi

@alirezafathi

4 years

Rui Huang, Wanyue Zhang, Thomas Funkhouser, Abhijit Kundu, Caroline Pantofaru, David A Ross, Alireza Fathi, An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

1

0

2

Alireza Fathi

@alirezafathi

4 months

🔥

Ahmet Iscen

@ahmetius

4 months

🔥 Calling all #CVPR2024 attendees! 🔥 Join us for the 1st Tool-Augmented VIsion (TAVI) Workshop on Monday morning in Summit 321! 💡 5 inspiring keynote talks 🎨 5 invited posters from the main conference Don't miss out! ➡️ More info:

1

8

23

0

2

Alireza Fathi

@alirezafathi

4 years

Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David A Ross, Brian E Brewington, Thomas Funkhouser, Caroline Pantofaru, Virtual Multi-view Fusion for 3D Semantic Segmentation

0

2

Alireza Fathi

@alirezafathi

4 years

Yue Wang, Alireza Fathi, Abhijit Kundu, David A. Ross, Caroline Pantofaru, Thomas Funkhouser, Justin Solomon, Pillar-based Object Detection for Autonomous Driving

1

2